© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4317
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax elements

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

    closing parentheses and braces in code.

    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
    msgTypes
    -0.56
    "],
    -0.51
    `;
    -0.47
    >");
    -0.46
    rillation
    -0.45
    '},
    -0.45
    [])
    -0.44
    HED
    -0.44
    ',
    -0.43
    formaz
    -0.42
    POSITIVE LOGITS
    ंदीखरीदारी
    0.60
    LookAnd
    0.48
    setVerticalGroup
    0.47
    曖昧さ回避
    0.47
     medesimo
    0.46
     automáticamente
    0.46
     mismos
    0.46
     mío
    0.45
     mesmos
    0.45
     appunto
    0.44
    Activations Density 0.135%

    No Known Activations