© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10016
    Prev
    Next
    INDEX
    Explanations

    action-oriented verbs that indicate a process or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.79
     للمعارف
    -0.77
    CloseOperation
    -0.72
    findpost
    -0.68
     يتيمه
    -0.67
    contentLoaded
    -0.65
    UnitTesting
    -0.64
     snippetHide
    -0.63
    AnchorStyles
    -0.63
    ValueStyle
    -0.62
    POSITIVE LOGITS
     *>(
    0.54
    {'
    0.51
     middel
    0.50
    {},
    0.48
     biais
    0.47
    ToAction
    0.46
    andosi
    0.46
    {}",
    0.46
    rak
    0.46
    {"
    0.46
    Activations Density 0.463%

    No Known Activations