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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 1310
    Prev
    Next
    INDEX
    Explanations

    HTML heading tags and their representation in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -2.33
    存于互联网档案馆
    -1.19
    DebuggerNonUser
    -1.16
    IsContent
    -1.13
    IsMutable
    -1.03
    sizeCache
    -1.03
    AnchorStyles
    -0.96
    NUMX
    -0.94
    Personensuche
    -0.93
    ConstraintMaker
    -0.93
    POSITIVE LOGITS
    migrations
    1.28
     noqa
    0.66
    h
    0.60
     pro
    0.60
    Migration
    0.57
    /
    0.53
     migrations
    0.53
     Lar
    0.51
     migration
    0.50
     Amar
    0.50
    Activations Density 0.007%

    No Known Activations