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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8361
    Prev
    Next
    INDEX
    Explanations

    specific symbols and formatting in mathematical or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AntiForgeryToken
    -0.45
    PreferredItem
    -0.37
     and
    -0.35
     BrowserModule
    -0.29
    principalColumn
    -0.29
     ģ
    -0.29
     essentiels
    -0.28
     or
    -0.27
     detenidos
    -0.27
     Verarbeitung
    -0.26
    POSITIVE LOGITS
     Administrativna
    0.91
    rungsseite
    0.84
     surla
    0.83
     müſſen
    0.82
     zuſammen
    0.78
     nakalista
    0.77
    ſicht
    0.76
    ロウィン
    0.75
     laſſen
    0.74
    <pad>
    0.73
    Activations Density 0.925%

    No Known Activations