© 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
    6. 13051
    Prev
    Next
    INDEX
    Explanations

    terms and symbols related to mathematical operations and properties, particularly in quantum mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    andidates
    -0.61
    ihnachts
    -0.60
     Jefus
    -0.59
    ategories
    -0.58
     innamor
    -0.58
    rieux
    -0.58
    šanu
    -0.58
     disorderly
    -0.57
    ollectionView
    -0.55
    URLException
    -0.54
    POSITIVE LOGITS
    Referanser
    0.72
    WebElementEntity
    0.65
    LikeLike
    0.61
    WriteAttribute
    0.53
    >';
    
    0.52
    bootstrapcdn
    0.50
    ">—
    0.49
    shall
    0.47
    WithIOException
    0.47
    Consumes
    0.47
    Activations Density 1.171%

    No Known Activations