© 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. 1438
    Prev
    Next
    INDEX
    Explanations

    C++ standard library syntax and function calls

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

    references to standard input/output streams in programming contexts

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

    irrelevant here, noise ratios

    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
     للاسماء
    -0.62
    ########.
    -0.62
     cappello
    -0.56
     jadx
    -0.56
    WriteTagHelper
    -0.56
     Nacionales
    -0.56
    fromCharCode
    -0.55
    ReferenceEquals
    -0.54
    }));
    
    -0.53
    Parcelize
    -0.51
    POSITIVE LOGITS
    usermodel
    0.64
    
    0.61
    }{*}{}
    0.60
    AnchorStyles
    0.55
    fatalError
    0.55
    omitempty
    0.55
    scriptId
    0.52
    UIControlState
    0.51
    reactstrap
    0.50
    וויק
    0.50
    Activations Density 0.038%

    No Known Activations