© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 62720
    Prev
    Next
    INDEX
    Explanations

    references to the subject and context of personal experiences or observations

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

    pronouns followed by negation/prohibition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缺少
    -0.64
     lacking
    -0.62
     missing
    -0.59
    missing
    -0.58
     lacked
    -0.57
     neglected
    -0.56
     missed
    -0.55
     lack
    -0.54
     falta
    -0.53
     failing
    -0.53
    POSITIVE LOGITS
     undes
    0.95
     shouldn
    0.95
     unwanted
    0.88
     unnecessary
    0.80
     shouldnt
    0.75
     undesirable
    0.72
     Shouldn
    0.72
     inappropriate
    0.68
    不该
    0.67
    不应该
    0.66
    Activations Density 0.116%

    No Known Activations