© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 63120
    Prev
    Next
    INDEX
    Explanations

    expressions of inaction or indifference in the context of social issues

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

    inaction and indifference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ativement
    -0.55
     فريبيس
    -0.48
    GraphicsUnit
    -0.48
    يكب
    -0.45
     الرياضيه
    -0.45
     BoxDecoration
    -0.44
    íncia
    -0.44
     SqlCommand
    -0.43
     ContentValues
    -0.43
    瘩
    -0.43
    POSITIVE LOGITS
     inaction
    0.58
     Prevention
    0.44
    AndEndTag
    0.43
     helplessly
    0.43
    ArrowToggle
    0.42
    writeFieldEnd
    0.41
    Prevention
    0.41
     komunitas
    0.41
     hjel
    0.41
     constaté
    0.41
    Activations Density 0.042%

    No Known Activations