© 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. 20-GEMMASCOPE-RES-131K
    11. 107187
    Prev
    Next
    INDEX
    Explanations

    syntactical structures and formatting elements in code or data representations

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

    code definitions and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.82
     ligiloj
    -0.77
    UrlResolution
    -0.70
    انجليز
    -0.68
     ddelweddau
    -0.66
    URLException
    -0.62
    лтамалар
    -0.60
    rungsseite
    -0.60
    новништво
    -0.60
     houſe
    -0.59
    POSITIVE LOGITS
     détaillé
    0.37
     CreateTagHelper
    0.36
     üzere
    0.34
    +:+
    0.33
     tâche
    0.32
     rendimiento
    0.32
    fjspx
    0.32
    getJSONArray
    0.32
     saveur
    0.31
    Enlaces
    0.31
    Activations Density 0.575%

    No Known Activations