© 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. 72763
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming concepts and functions

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

    just

    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
    httphttps
    -0.61
    ↹
    -0.59
     ModelExpression
    -0.58
    RTGC
    -0.54
     Мексичка
    -0.54
     esternos
    -0.54
    BeginInit
    -0.53
    しか
    -0.53
    bootstrapcdn
    -0.53
    TargetException
    -0.51
    POSITIVE LOGITS
     simply
    3.13
     simplemente
    2.72
    simply
    2.70
     just
    2.66
     просто
    2.59
     simplesmente
    2.50
     semplicemente
    2.48
     einfach
    2.39
     simplement
    2.38
     Simply
    2.31
    Activations Density 0.541%

    No Known Activations