© 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. 8-GEMMASCOPE-RES-16K
    11. 5607
    Prev
    Next
    INDEX
    Explanations

    tokens that denote sections or structural elements in code or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ea
    -0.46
    нья
    -0.46
    ண்
    -0.45
     Seas
    -0.43
     nuage
    -0.40
    ny
    -0.40
    iri
    -0.39
    uglify
    -0.39
     blad
    -0.39
    et
    -0.38
    POSITIVE LOGITS
    <bos>
    0.99
    awtextra
    0.98
    الحياه
    0.97
    رشف
    0.95
    BeginContext
    0.93
     Савезне
    0.87
     saites
    0.85
    IndentedString
    0.84
    MigrationBuilder
    0.83
    ConstraintMaker
    0.82
    Activations Density 0.289%

    No Known Activations