© 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. 27874
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols used in equations and functions

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

    algebraic expressions and formulas

    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
     betweenstory
    -0.71
    httphttps
    -0.69
    pushFollow
    -0.64
    uxxxx
    -0.58
     propOrder
    -0.57
     صوتيه
    -0.56
     invokingState
    -0.54
     فريبيس
    -0.54
     '\\;'
    -0.54
    oneofs
    -0.52
    POSITIVE LOGITS
     Ambiental
    0.36
    льше
    0.35
    kundige
    0.34
     Internasional
    0.33
     vyu
    0.33
     internasional
    0.32
     makl
    0.32
     Erkrank
    0.32
     Jezus
    0.31
     avulla
    0.30
    Activations Density 1.500%

    No Known Activations