© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15563
    Prev
    Next
    INDEX
    Explanations

    sections with structured data or tables, including numerical results and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 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
    pecabe
    -0.83
    findpost
    -0.71
    iodía
    -0.66
    hæng
    -0.64
     vœ
    -0.64
    arangay
    -0.63
     Sénat
    -0.63
    SharedCtor
    -0.62
    ientras
    -0.60
     enfans
    -0.60
    POSITIVE LOGITS
    subsubsection
    0.44
    inaldi
    0.35
    ...
    0.35
    ρισ
    0.33
    …
    0.32
     Morty
    0.30
     AVL
    0.30
     anal
    0.29
    ots
    0.29
     endwhile
    0.29
    Activations Density 0.458%

    No Known Activations