© 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. 7-GEMMASCOPE-RES-16K
    6. 7363
    Prev
    Next
    INDEX
    Explanations

    references to the audience or viewer experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Goode
    -0.83
     =>'
    -0.73
     Wilkins
    -0.63
     Mercier
    -0.63
     Baxter
    -0.62
    볍
    -0.60
     monasterio
    -0.60
    σιμοποι
    -0.60
     Wilma
    -0.59
     sepol
    -0.59
    POSITIVE LOGITS
     audience
    1.97
    audience
    1.79
     audiences
    1.77
     Audience
    1.75
    Audience
    1.67
    Audiences
    1.34
    audi
    1.23
     publiek
    1.19
     Audi
    1.12
     crowd
    1.12
    Activations Density 0.068%

    No Known Activations