Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6422
    Prev
    Next
    INDEX
    Explanations

    questions that inquire about specific information or factual details

    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
    LookAnd
    -0.83
    MigrationBuilder
    -0.78
     ujednoznacz
    -0.77
    expandindo
    -0.77
    multer
    -0.75
    RTEE
    -0.73
     الرياضيه
    -0.73
    UserScript
    -0.73
     дописавши
    -0.72
    IContainer
    -0.71
    POSITIVE LOGITS
    GOTREF
    0.52
     asimismo
    0.50
    جغرافيا
    0.47
     něm
    0.45
     informací
    0.44
     educativos
    0.43
     financière
    0.43
    kmal
    0.43
    jego
    0.43
     szint
    0.43
    Activations Density 0.269%

    No Known Activations