© 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. 16978
    Prev
    Next
    INDEX
    Explanations

    programming syntax and constructs related to data manipulation

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

    variable declarations and resource management

    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
    ospor
    -0.37
     Horizon
    -0.36
     mur
    -0.36
     pompe
    -0.35
    little
    -0.35
     big
    -0.34
     LITTLE
    -0.34
    ciclop
    -0.34
     bmp
    -0.34
     HOR
    -0.33
    POSITIVE LOGITS
    var
    0.96
    Personendaten
    0.77
     var
    0.76
    LookAnd
    0.75
     betweenstory
    0.64
     the
    0.64
    fjspx
    0.61
     readonly
    0.61
    featureID
    0.57
    Diweddarwch
    0.56
    Activations Density 0.005%

    No Known Activations