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. 6431
    Prev
    Next
    INDEX
    Explanations

    parentheses in various formats and 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
     appelez
    -0.62
    saraba
    -0.61
     متحده
    -0.60
    writeFieldEnd
    -0.56
    verwijspagina
    -0.54
    啶
    -0.53
    المل
    -0.52
    ว์
    -0.52
    \}.
    -0.52
    ]='\
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.78
    RunWith
    0.65
    migrationBuilder
    0.61
     équilibre
    0.57
    udades
    0.54
    ctivas
    0.54
    TabIndex
    0.54
     lungs
    0.53
     sauvages
    0.53
    tocks
    0.53
    Activations Density 0.297%

    No Known Activations