© 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. 9-GEMMASCOPE-RES-131K
    11. 41705
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "calc" and its variations related to calculating or analysis in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    elemental analysis calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    UserScript
    -0.52
     fontFamily
    -0.50
    dtos
    -0.48
     ostavi
    -0.47
    ›
    -0.47
    <%@
    -0.46
     marginTop
    -0.46
    rootView
    -0.44
     itemId
    -0.44
     dian
    -0.44
    POSITIVE LOGITS
    calc
    2.17
     calc
    2.06
    Calc
    1.95
     Calc
    1.95
     CALC
    1.41
    CALC
    1.37
     Calculator
    0.97
     CALCUL
    0.93
     kalk
    0.90
     calculator
    0.88
    Activations Density 0.003%

    No Known Activations