© 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. 3698
    Prev
    Next
    INDEX
    Explanations

    code structure elements related to variable declarations and definitions

    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
     Référence
    -0.94
     متعلقه
    -0.88
    InvalidProtocol
    -0.84
    writeFieldEnd
    -0.82
    mappedBy
    -0.79
    ఔ
    -0.76
    featureID
    -0.76
     للاسماء
    -0.75
    WritableDatabase
    -0.72
     Zlat
    -0.70
    POSITIVE LOGITS
    enumi
    0.43
    resolve
    0.40
    {{
    0.39
    reduce
    0.38
    ={{
    0.37
    wikimedia
    0.37
    ResponseWriter
    0.35
    coder
    0.35
    IA
    0.34
     위해
    0.34
    Activations Density 0.069%

    No Known Activations