© 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. 1435
    Prev
    Next
    INDEX
    Explanations

    API request method declarations and parameters

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

    API request parameters and status indicators related to HTTP methods

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

    http methods

    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
     Waterfront
    -0.48
    InjectAttribute
    -0.48
    わら
    -0.46
    دام
    -0.46
    timeScale
    -0.45
     '\\;'
    -0.44
     Scand
    -0.43
    CAPTION
    -0.43
     huom
    -0.43
    👓
    -0.42
    POSITIVE LOGITS
     POST
    1.37
     post
    1.31
    POST
    1.27
    post
    1.18
     Post
    1.17
    Post
    1.10
     GET
    1.04
     пост
    0.96
    GET
    0.94
     PUT
    0.86
    Activations Density 0.124%

    No Known Activations