© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 675
    Prev
    Next
    INDEX
    Explanations

    structured data and specific terms related to game downloads and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical data and technical terms related to scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Formula 1, Circuits, Conspiracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.59
    <eos>
    -0.57
    ↵↵↵↵
    -0.47
     but
    -0.44
     
    -0.44
     We
    -0.43
     "
    -0.43
     ‘
    -0.43
     (
    -0.42
     para
    -0.41
    POSITIVE LOGITS
     GenerationType
    1.03
    :.
    0.99
    ,.
    0.97
    .
    0.96
     &.
    0.91
    .".
    0.88
    .'.
    0.87
     externi
    0.86
    клопе
    0.86
     :.
    0.85
    Activations Density 0.127%

    No Known Activations