© 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. 14922
    Prev
    Next
    INDEX
    Explanations

    code structure elements like functions and classes

    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
     Roskov
    -0.87
    Geplaatst
    -0.79
    انيف
    -0.77
    LookAnd
    -0.72
    IVEREF
    -0.68
    CloseOperation
    -0.64
    хьтан
    -0.62
    SequentialGroup
    -0.60
     parliamentary
    -0.59
    principalColumn
    -0.59
    POSITIVE LOGITS
    providedIn
    0.60
    MENAFN
    0.53
     strategis
    0.52
    WebMethod
    0.49
    DispatchToProps
    0.49
    ніципалі
    0.47
     efficaces
    0.47
    Przypisy
    0.47
    diğimiz
    0.44
     efficace
    0.44
    Activations Density 0.031%

    No Known Activations