© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4225
    Prev
    Next
    INDEX
    Explanations

    mentions of professionals in various fields, particularly educators and legal experts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.72
    Obrázky
    -0.67
     الرياضيه
    -0.59
    లాలు
    -0.55
    <_>
    -0.54
     nahilalakip
    -0.53
    court
    -0.52
    outine
    -0.49
    ồn
    -0.48
    KommentareTeilen
    -0.48
    POSITIVE LOGITS
    providedIn
    0.53
     lectured
    0.52
    帖最后由
    0.52
    EXPER
    0.50
     expert
    0.49
     discusses
    0.49
    — 
    0.48
     representatives
    0.48
     keynote
    0.48
    Kenapa
    0.48
    Activations Density 0.227%

    No Known Activations