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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 23182
    Prev
    Next
    INDEX
    Explanations

    formatting and markup elements commonly used in programming or documentation

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

    compression or data formatting tags

    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
    queryInterface
    -0.39
    XMLSchema
    -0.38
    YourGuide
    -0.37
     fundido
    -0.36
     colocación
    -0.35
    toHaveBeen
    -0.35
     problemet
    -0.35
     waveforms
    -0.35
    tructuring
    -0.34
     geométrico
    -0.34
    POSITIVE LOGITS
    ChildScrollView
    0.63
    SuppressLint
    0.58
     desertcart
    0.55
     للاسماء
    0.54
    jsxFileName
    0.54
     Normdatei
    0.52
    findpost
    0.52
    ngdoc
    0.50
     createState
    0.50
    astify
    0.49
    Activations Density 0.007%

    No Known Activations