© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1695
    Prev
    Next
    INDEX
    Explanations

    numerical data related to measurements and statistical analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical measurements and statistical data (like percentages, numerical ranges, scores).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    numerical values and measurements, particularly those related to statistics, percentages, and scientific data points.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    expressions reporting precise numerical measurements, especially decimals, percentages, and values paired with units or rates.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    numerical measurements with units (percentages, weights, speeds, distances, etc.).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.93
    enumii
    -0.80
    uxxxx
    -0.77
     ویکی‌آمباردا
    -0.66
    #+#
    -0.65
    IsMutable
    -0.65
    ﭔ
    -0.64
    <unused43>
    -0.63
    <unused41>
    -0.63
    <unused8>
    -0.63
    POSITIVE LOGITS
     dopiero
    0.40
    horabuena
    0.37
     sedangkan
    0.35
     instead
    0.35
     Durchsch
    0.34
     plutôt
    0.32
     jopa
    0.31
     istället
    0.31
    instead
    0.31
     mourut
    0.31
    Activations Density 0.590%

    No Known Activations