Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 87080
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the significance of various subjects or concepts

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

    importance of

    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
     quelque
    -0.47
    Pautan
    -0.39
    <_>
    -0.36
     kuiten
    -0.35
     forState
    -0.34
     idéia
    -0.34
     Atau
    -0.33
     irgend
    -0.33
    Fprintf
    -0.33
     maybe
    -0.32
    POSITIVE LOGITS
     Importance
    0.89
    Importance
    0.78
     importance
    0.78
    importance
    0.73
     penting
    0.71
     Important
    0.70
    Importante
    0.68
    importanza
    0.68
     Vital
    0.67
    的重要性
    0.66
    Activations Density 0.011%

    No Known Activations