© 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 - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2451
    Prev
    Next
    INDEX
    Explanations

    class declarations and names within programming-related text

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

    Code that uses "extends" keyword

    np_acts-logits-general · gemini-2.0-flash

    class extension or implementation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *);
    -0.61
    %);
    -0.60
    .);
    -0.59
    %;
    -0.57
    );
    -0.56
    』『
    -0.54
     ModelExpression
    -0.53
     '');
    -0.53
    !);
    -0.53
    .;
    -0.50
    POSITIVE LOGITS
    __':
    
    0.92
     extends
    0.89
    __":
    
    0.78
    __':
    0.77
    __":
    0.71
     implements
    0.70
     Drapeau
    0.69
    IntoConstraints
    0.66
    ControllerAdvice
    0.65
    EndInit
    0.64
    Activations Density 0.121%

    No Known Activations