© 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. 15-GEMMASCOPE-RES-16K
    6. 8829
    Prev
    Next
    INDEX
    Explanations

    intense emotional expressions or punctuation conveying strong feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    databind
    -0.95
     oprot
    -0.82
    }{*}{
    -0.81
    djangoproject
    -0.80
    Abit
    -0.78
    المناصب
    -0.77
    banez
    -0.76
    kegaard
    -0.73
    ertale
    -0.73
     Glanz
    -0.72
    POSITIVE LOGITS
    ?????
    0.90
    !!!!!
    0.86
    .........
    0.85
    ffffff
    0.81
    !!!!
    0.77
    Cama
    0.75
    ooooo
    0.73
    loroethene
    0.73
    хоро
    0.73
    tutorials
    0.72
    Activations Density 0.204%

    No Known Activations