© 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. 11-GEMMASCOPE-RES-16K
    11. 8799
    Prev
    Next
    INDEX
    Explanations

    references to clinical trials and medical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disques
    -0.44
    ætte
    -0.37
     pega
    -0.34
    addContainerGap
    -0.34
     commandement
    -0.33
    Sticker
    -0.33
    dsk
    -0.33
     symboles
    -0.32
    atschapp
    -0.32
     pegatina
    -0.32
    POSITIVE LOGITS
     propOrder
    0.58
    HideFlags
    0.55
    无所
    0.52
     ModelExpression
    0.50
    apimachinery
    0.49
    logous
    0.48
     opti
    0.44
    รรม
    0.44
    bolista
    0.44
     وتسجيلات
    0.43
    Activations Density 0.586%

    No Known Activations