Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12963
    Prev
    Next
    INDEX
    Explanations

    various types of error messages and server response details

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

    Alphanumeric strings and code snippets

    np_acts-logits-general · gemini-2.0-flash

    closing code or data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amaño
    -0.77
    ربای
    -0.76
     Dummies
    -0.76
     ſind
    -0.74
    NUMX
    -0.73
     Anſ
    -0.72
     photolibrary
    -0.71
     Efq
    -0.71
    xase
    -0.70
     $_(
    -0.69
    POSITIVE LOGITS
    ";
    
    1.41
    );
    
    1.38
    "));
    
    1.37
    ");
    
    1.32
    "));
    1.31
    ";
    1.27
    ");
    1.26
    ));
    
    1.26
    );
    1.25
    ));
    1.24
    Activations Density 7.423%

    No Known Activations