© 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-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 680
    Prev
    Next
    INDEX
    Explanations

    online medical advice and safety guidelines

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

    conditions and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.42
    charCode
    -0.38
    ViewImports
    -0.36
     various
    -0.36
     sometimes
    -0.35
     jopa
    -0.35
     bazen
    -0.34
     niektor
    -0.33
    XtraReports
    -0.33
     several
    -0.33
    POSITIVE LOGITS
     للاسماء
    0.59
     незавершена
    0.59
    FunctionFlags
    0.55
     faſt
    0.54
     ſtate
    0.52
     ویکی‌پدی
    0.52
     autorytatywna
    0.51
     Monfieur
    0.50
     ModelExpression
    0.50
     noDo
    0.50
    Activations Density 0.083%

    No Known Activations