© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 9988
    Prev
    Next
    INDEX
    Explanations

    references to quests and hunting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.77
    WireFormatLite
    -0.73
    AccessorTable
    -0.69
    ()]);
    -0.65
    zzá
    -0.63
     addSubview
    -0.57
    ThroughAttribute
    -0.57
    WindowConstants
    -0.56
    principalTable
    -0.54
    ollectionView
    -0.53
    POSITIVE LOGITS
     hunt
    1.76
     quest
    1.65
     search
    1.60
     HUNT
    1.35
    hunt
    1.35
     hunts
    1.34
    Hunt
    1.31
     hunting
    1.28
     Quest
    1.26
    search
    1.24
    Activations Density 0.061%

    No Known Activations