© 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. 12280
    Prev
    Next
    INDEX
    Explanations

    references to specific names, brands, or products, particularly related to transportation or technology

    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
    /**
    -1.29
     Lovato
    -0.98
    argout
    -0.95
     مرئيه
    -0.94
    WebElementEntity
    -0.92
    Chandler
    -0.89
    RuleContext
    -0.87
     Reiki
    -0.86
     Colton
    -0.86
     Keene
    -0.85
    POSITIVE LOGITS
    

    0.74
     Frit
    0.70
     Borg
    0.64
    slices
    0.63
    lidays
    0.62
     gäng
    0.61
    aarrggbb
    0.60
    нивер
    0.60
    Clos
    0.60
    cangan
    0.59
    Activations Density 0.975%

    No Known Activations