© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 4680
    Prev
    Next
    INDEX
    Explanations

    pieces of code related to sets and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.79
    SequentialGroup
    -0.72
     resourceCulture
    -0.71
     समीक्षाएं
    -0.71
     Predict
    -0.70
    서는
    -0.69
     prediction
    -0.66
     ModelExpression
    -0.66
     Prediction
    -0.65
    FTFY
    -0.63
    POSITIVE LOGITS
    oblastoma
    0.49
     chinoise
    0.46
    TableAdapter
    0.46
    NSIndexPath
    0.46
    toMatchSnapshot
    0.43
     FBref
    0.43
     ziekte
    0.42
    ิลปะ
    0.42
    XtraBars
    0.42
    EnumMember
    0.42
    Activations Density 0.137%

    No Known Activations