© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17470
    Prev
    Next
    INDEX
    Explanations

    different forms of a specific programming language, indicating a focus on Lua-related keywords and syntax

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

    lu-cans, lu-con, lu-atex

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Italijanski
    -0.47
    ngdoc
    -0.46
     colgante
    -0.45
    šče
    -0.45
    initComponents
    -0.45
     bonté
    -0.44
     antigüedad
    -0.43
    žius
    -0.43
    ukų
    -0.43
    subsubsection
    -0.42
    POSITIVE LOGITS
    lu
    2.73
    LU
    1.92
     lu
    1.86
    Lu
    1.75
     Lu
    1.73
     LU
    1.56
    лу
    1.30
    lue
    1.17
    lution
    1.15
    ilu
    1.14
    Activations Density 0.014%

    No Known Activations