© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7801
    Prev
    Next
    INDEX
    Explanations

    character descriptions and their roles in a narrative

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

    Aftermath of a defeat

    np_acts-logits-general · gemini-2.0-flash

    don armage's defeat and destruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lolita
    -0.47
    IntoConstraints
    -0.46
     fieldNum
    -0.45
     Deco
    -0.45
     GTO
    -0.45
     Cowboy
    -0.44
    untura
    -0.43
    Cowboy
    -0.43
    nsics
    -0.42
     trot
    -0.42
    POSITIVE LOGITS
     powerful
    0.57
     corrupted
    0.50
    powerful
    0.47
     powers
    0.46
     corruption
    0.46
    adpleegd
    0.46
     puissante
    0.45
     corrom
    0.45
     poderes
    0.45
     fight
    0.45
    Activations Density 0.839%

    No Known Activations