© 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. 3-GEMMASCOPE-RES-16K
    11. 13068
    Prev
    Next
    INDEX
    Explanations

    names of individuals and specific entities involved in legal contexts

    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
     وتسجيلات
    -0.68
    enumi
    -0.63
    aarrggbb
    -0.58
    ícola
    -0.53
    RunWith
    -0.52
    itemCount
    -0.51
     հղումներ
    -0.51
     autorytatywna
    -0.50
    RESUMO
    -0.50
    withstanding
    -0.50
    POSITIVE LOGITS
    yntaxException
    0.61
    rehensive
    0.53
     GetEnumerator
    0.52
    dotenv
    0.52
    Билгалдахарш
    0.50
    ArgsConstructor
    0.49
    Indented
    0.49
     essentielles
    0.48
    ResponseWriter
    0.48
    chossen
    0.48
    Activations Density 0.381%

    No Known Activations