© 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. 21-GEMMASCOPE-RES-16K
    11. 15803
    Prev
    Next
    INDEX
    Explanations

    actions or movements related to attention and interaction between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Breakdown
    -0.33
     serons
    -0.32
     proche
    -0.30
     plancher
    -0.29
     kø
    -0.29
     provoquer
    -0.28
     pit
    -0.28
     akad
    -0.28
     proches
    -0.27
    저
    -0.27
    POSITIVE LOGITS
    errHandler
    0.75
    styleType
    0.58
     estekak
    0.58
    ➟
    0.56
     AssemblyCompany
    0.56
     Turning
    0.55
     viewType
    0.54
    ScopeManager
    0.54
     glances
    0.53
    SharedCtor
    0.53
    Activations Density 0.152%

    No Known Activations