© 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. 12-GEMMASCOPE-RES-16K__L0-22
    6. 1067
    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
     ModelExpression
    -0.66
    }{*}{
    -0.66
    CORD
    -0.65
    //
    -0.62
     person
    -0.58
     مشين
    -0.56
     MediatR
    -0.56
    ExecuteReader
    -0.56
     
    -0.55
    fertigung
    -0.54
    POSITIVE LOGITS
    
    0.68
    tvguidetime
    0.67
    tagHelperRunner
    0.65
     Bastille
    0.62
     Aarhus
    0.61
     diffusivity
    0.61
    
    0.59
    </thead>
    0.59
     Euclid
    0.59
     stiefel
    0.58
    Activations Density 0.003%

    No Known Activations