© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 34522
    Prev
    Next
    INDEX
    Explanations

    references to guidelines or instructions related to checking or verifying information

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

    check account balance

    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
     estekak
    -0.45
    multer
    -0.44
     ligiloj
    -0.44
    Życiorys
    -0.44
     MainAxisSize
    -0.43
    niająca
    -0.39
     betweenstory
    -0.35
    ագրություններ
    -0.34
    /**
    -0.33
    TypedDataSet
    -0.32
    POSITIVE LOGITS
     check
    2.14
     checking
    2.03
    check
    1.92
     checked
    1.91
     Check
    1.91
     checks
    1.88
    Check
    1.82
     Checking
    1.77
     CHECK
    1.76
    checking
    1.72
    Activations Density 0.139%

    No Known Activations