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. 159
    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
    ReusableCell
    -0.72
     cref
    -0.72
    writeField
    -0.68
     Мексичка
    -0.65
    AnimationsModule
    -0.63
    äher
    -0.63
    posedge
    -0.63
    GEBURTSDATUM
    -0.63
    MigrationBuilder
    -0.63
    CloseOperation
    -0.62
    POSITIVE LOGITS
     carefully
    0.58
    干脆
    0.56
     Carefully
    0.52
     lieber
    0.49
     kurzer
    0.49
     resorted
    0.48
     Bourgoin
    0.47
     zog
    0.47
     cuidadosamente
    0.46
     careful
    0.46
    Activations Density 0.180%

    No Known Activations