© 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. 31-GEMMASCOPE-RES-16K
    11. 14560
    Prev
    Next
    INDEX
    Explanations

    instances of measurements and their implications

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

    measurements, quantitative data, and "for the first time" phrases in scientific or technical contexts.

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

    phrases that establish something or report findings for the first time.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    formal scientific or technical language describing measurements, methods, or establishing facts for the first time.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    formal, method-oriented statements that describe measurements, procedures, criteria, or first-time/result-establishing claims in technical or instructional contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.47
     lenker
    -0.47
     Majefty
    -0.46
    RenderAtEndOf
    -0.44
     faſt
    -0.42
    lgari
    -0.40
    цездатний
    -0.39
    tinyos
    -0.38
    .*")]
    -0.37
    Искәрмәләр
    -0.35
    POSITIVE LOGITS
    tothe
    0.73
    到
    0.68
     to
    0.65
     zum
    0.57
     To
    0.56
    至
    0.56
    To
    0.54
     到
    0.52
    SBATCH
    0.50
     zur
    0.48
    Activations Density 0.565%

    No Known Activations