© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 748
    Prev
    Next
    INDEX
    Explanations

    code-related structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    structures related to code or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ActionCreators
    -0.61
    setupUi
    -0.57
    IOUtils
    -0.52
    DockStyle
    -0.51
    astify
    -0.50
     "..\..\
    -0.49
     makeStyles
    -0.49
     DriverManager
    -0.49
    AnimationsModule
    -0.49
     onPostExecute
    -0.47
    POSITIVE LOGITS
     int
    1.18
    int
    1.16
    boolean
    0.96
     bool
    0.92
     boolean
    0.91
    bool
    0.88
    double
    0.82
    String
    0.81
     String
    0.81
    Boolean
    0.79
    Activations Density 0.070%

    No Known Activations