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. 92
    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
    >>()
    -0.70
     calendriers
    -0.59
     SEDS
    -0.56
    lioma
    -0.55
    TagMode
    -0.55
    
    -0.54
    ++]=
    -0.54
    Bav
    -0.53
    "]));
    -0.53
    tagHelperRunner
    -0.53
    POSITIVE LOGITS
    OrWhiteSpace
    0.66
     isInitialized
    0.65
    TryParse
    0.63
     sanitaires
    0.60
     enfans
    0.60
     hasNext
    0.60
     qualcuno
    0.59
     prêtres
    0.59
    hasOwnProperty
    0.58
    isSuccessful
    0.57
    Activations Density 0.069%

    No Known Activations