© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9717
    Prev
    Next
    INDEX
    Explanations

    recommendations and encouraging readers to explore books or resources

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

    recommendations and calls to action encouraging the reader to try, check out, or purchase something.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gradually
    -0.35
     CallOverrides
    -0.34
     malheure
    -0.34
     köz
    -0.33
     muun
    -0.32
     avancé
    -0.32
     Comprometido
    -0.31
     petugas
    -0.31
     useState
    -0.31
     naj
    -0.30
    POSITIVE LOGITS
     NSCoder
    0.77
     visit
    0.73
     check
    0.71
     Visit
    0.69
    visit
    0.66
    ぜひ
    0.64
     checkout
    0.62
     Check
    0.61
    évaluateur
    0.61
     Definitely
    0.61
    Activations Density 0.180%

    No Known Activations