© 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. 35-GEMMASCOPE-RES-16K
    11. 14469
    Prev
    Next
    INDEX
    Explanations

    references to paper and its various usages and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.65
    RenderAtEndOf
    -0.64
     AssemblyCulture
    -0.64
    iſche
    -0.63
    ロウィン
    -0.63
    ﹧
    -0.62
    niſſe
    -0.61
    makeConstraints
    -0.61
    UserScript
    -0.60
    bootstrapcdn
    -0.60
    POSITIVE LOGITS
     paper
    3.59
    paper
    3.08
     Paper
    3.03
    Paper
    2.95
     PAPER
    2.80
     papers
    2.72
    PAPER
    2.50
     Papers
    2.31
    papers
    2.27
    纸
    2.25
    Activations Density 0.520%

    No Known Activations