© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 15388
    Prev
    Next
    INDEX
    Explanations

    control structure keywords in programming, such as conditionals and block initiators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waller
    -0.58
     frescas
    -0.48
    createCanvas
    -0.48
    ViewChild
    -0.47
    Varint
    -0.47
    ława
    -0.47
     oxygen
    -0.46
     _$
    -0.46
     World
    -0.46
    関連項目
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.92
    RenderAtEndOf
    0.76
    });*/
    0.74
    ніципалі
    0.73
    nachron
    0.70
    TAWA
    0.69
    ɵɵelementStart
    0.68
    UnusedPrivate
    0.66
    الحياه
    0.64
    --){
    0.63
    Activations Density 0.350%

    No Known Activations