© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 522
    Prev
    Next
    INDEX
    Explanations

    references to transparency and public accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    public information or accessibility

    np_acts-logits-general · gemini-2.0-flash

    publicly available information

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    RenderAtEndOf
    -0.41
     ingår
    -0.30
    verifyException
    -0.30
    AccessorTable
    -0.29
     Prüf
    -0.29
     sti
    -0.28
    ultades
    -0.28
    pezifische
    -0.28
     specialist
    -0.27
     geç
    -0.27
    POSITIVE LOGITS
     publicly
    0.88
    公開
    0.85
     transparency
    0.84
     Transparency
    0.82
     openness
    0.82
     pública
    0.77
     ComVisible
    0.77
    Transparency
    0.77
     openly
    0.76
     öffentlich
    0.73
    Activations Density 0.417%

    No Known Activations