© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 83162
    Prev
    Next
    INDEX
    Explanations

    references to personal protection and safety measures against hazardous materials

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

    avoiding harmful contact

    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
    parsedMessage
    -0.58
    richTextPanel
    -0.55
    delwed
    -0.55
    +#+#
    -0.55
    oneofs
    -0.55
     Вікі
    -0.51
     ویکی‌پدی
    -0.51
    лтамалар
    -0.50
    Földrajzportál
    -0.49
    xase
    -0.49
    POSITIVE LOGITS
    Avoid
    0.42
     Infór
    0.42
     sanitarias
    0.41
    исленность
    0.40
     contacting
    0.38
     avoidance
    0.38
     productivo
    0.38
     identité
    0.36
    printStackTrace
    0.35
     extiende
    0.35
    Activations Density 0.001%

    No Known Activations