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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1680
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical estimation and limitations

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

    Begins with "under" and relates to math/tax

    np_acts-logits-general · gemini-2.0-flash

    under and low

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.45
     turístico
    -0.44
    crisy
    -0.38
    catus
    -0.38
    caux
    -0.36
     bekämp
    -0.35
     powy
    -0.35
    nteral
    -0.34
    การณ์
    -0.34
    atoday
    -0.34
    POSITIVE LOGITS
     low
    1.02
     lowly
    0.96
     Low
    0.86
     lowest
    0.83
    Low
    0.83
     Lowest
    0.80
    低
    0.80
     düşük
    0.80
     LOW
    0.79
     rendah
    0.79
    Activations Density 1.316%

    No Known Activations