© 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. 9-GEMMASCOPE-RES-16K
    11. 8745
    Prev
    Next
    INDEX
    Explanations

    terms associated with control, prevention, and intervention strategies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.46
    xymatrix
    -0.34
    Separated
    -0.33
    ROIT
    -0.32
    ResponseWriter
    -0.32
     ws
    -0.32
    ngrx
    -0.31
    Nichts
    -0.31
    infra
    -0.31
    ofern
    -0.30
    POSITIVE LOGITS
     prevention
    0.75
    Prevention
    0.71
    prevention
    0.70
    を抑
    0.70
    抑制
    0.70
    Preventing
    0.69
     suppressing
    0.68
     suppression
    0.66
     suppress
    0.65
     combating
    0.64
    Activations Density 0.700%

    No Known Activations