© 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. 14852
    Prev
    Next
    INDEX
    Explanations

    patterns of mathematical or programming syntax involving variables and operations

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

    numeric digits and mathematical/scientific notation with exponents and operators.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    AsUp
    -0.66
    脚注の使い方
    -0.65
    存于互联网档案馆
    -0.62
     ब्रेकडाउन
    -0.60
     ModelExpression
    -0.60
     disambiguazione
    -0.60
    rungsseite
    -0.59
    Autoritní
    -0.56
    zzleHttp
    -0.56
    oa̍t
    -0.56
    POSITIVE LOGITS
    zero
    0.47
     zero
    0.46
    vun
    0.37
    Zero
    0.34
     wypo
    0.34
    <0x80>
    0.34
     precursor
    0.33
    ZERO
    0.33
     zéro
    0.33
    arvi
    0.33
    Activations Density 0.831%

    No Known Activations