© 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. 115888
    Prev
    Next
    INDEX
    Explanations

    questions and prompts related to character engagement and emotional response in stories

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

    questions starting with wh words

    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
    extAlignment
    -0.81
     autorytatywna
    -0.79
    parsedMessage
    -0.67
    expandindo
    -0.65
    RenderAtEndOf
    -0.62
    
    -0.62
     صوتيه
    -0.61
    posedge
    -0.60
     geſch
    -0.59
    ſelben
    -0.57
    POSITIVE LOGITS
    What
    0.71
     why
    0.69
     What
    0.68
     how
    0.66
     what
    0.66
    How
    0.63
    Why
    0.62
    why
    0.60
     How
    0.59
     does
    0.58
    Activations Density 0.007%

    No Known Activations