© 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. 13-GEMMASCOPE-RES-65K
    11. 14754
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate seeking or discovering information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gré
    -0.63
     MacGregor
    -0.59
     multi
    -0.57
     hamb
    -0.56
     Multi
    -0.56
    IsNotEmpty
    -0.55
    TextFormField
    -0.55
     Smith
    -0.54
    FileData
    -0.54
     Pal
    -0.53
    POSITIVE LOGITS
     AssemblyCulture
    1.28
    principalTable
    1.09
    jooq
    0.98
     Découvrez
    0.94
     Descub
    0.94
    OGND
    0.92
     Descubre
    0.91
     expéri
    0.88
     MonoBehaviour
    0.85
    Know
    0.85
    Activations Density 0.010%

    No Known Activations