© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2308
    Prev
    Next
    INDEX
    Explanations

    code related to data fetching and state management in a Redux application

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

    Code related to reducers

    np_acts-logits-general · gemini-2.0-flash

    different type names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sire
    -0.45
     consentimiento
    -0.42
     Scar
    -0.42
    WebControls
    -0.41
     Harn
    -0.41
    createCanvas
    -0.41
    enterOuterAlt
    -0.39
    umon
    -0.39
    Spons
    -0.39
    ortive
    -0.39
    POSITIVE LOGITS
     reducer
    1.09
    reducer
    1.04
     Reducer
    1.02
    redux
    0.97
     reducers
    0.97
    Reducer
    0.95
     rootReducer
    0.92
    ActionCreators
    0.92
    reducers
    0.92
     REDUC
    0.92
    Activations Density 0.082%

    No Known Activations