© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15289
    Prev
    Next
    INDEX
    Explanations

    elements related to HTTP request and response structures

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

    Code snippets, often headers or options

    np_acts-logits-general · gemini-2.0-flash

    programming keywords followed by parentheses

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     StatelessWidget
    -0.70
    :+:
    -0.57
    Rhestr
    -0.57
     &___
    -0.56
     tartalomajánló
    -0.54
     ModelExpression
    -0.53
     HasFactory
    -0.51
    Personensuche
    -0.51
     الدولى
    -0.50
    .*")]
    -0.49
    POSITIVE LOGITS
     quæ
    0.71
     ddelweddau
    0.67
    ().
    0.66
    ThemeOverlay
    0.65
    Portale
    0.60
    WebServlet
    0.59
     myſelf
    0.56
     Sarm
    0.55
     tauto
    0.55
     auffi
    0.54
    Activations Density 0.137%

    No Known Activations