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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K__L0-22
    6. 32
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.14
    )');
    -0.87
    IsMutable
    -0.85
    UnusedPrivate
    -0.81
    )");
    
    -0.81
    __':
    
    -0.74
    енча
    -0.73
    ')")
    -0.73
    >");
    
    -0.73
    SerializedSize
    -0.72
    POSITIVE LOGITS
    \{\\
    0.82
    escaping
    0.69
    WriteLiteral
    0.69
    ọi
    0.63
     թվական
    0.60
    ⎪
    0.59
     Bout
    0.59
     .=
    0.58
    reactstrap
    0.57
    addGap
    0.57
    Activations Density 0.011%

    No Known Activations