© 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. 1425
    Prev
    Next
    INDEX
    Explanations

    specific proper names and their occurrences in the text

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

    references to specific names or entities

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

    Rozikov, Razaleigh, Requests

    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
     VIDEOTAPE
    -0.55
     sécher
    -0.47
     alguna
    -0.46
    NavigationBar
    -0.46
    AppComponent
    -0.46
    ModelAdmin
    -0.44
    sidemargin
    -0.43
    PageIndex
    -0.43
     presencia
    -0.42
    立った
    -0.42
    POSITIVE LOGITS
    RectangleBorder
    0.74
     doInBackground
    0.67
    SourceChecksum
    0.65
     MainAxisSize
    0.63
    談社
    0.63
     bulge
    0.62
    <()>
    0.62
     <>",
    0.62
     useRouter
    0.61
    endpush
    0.61
    Activations Density 0.001%

    No Known Activations