© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 66375
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements in code snippets

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

    code block endings

    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
    ScopeManager
    -0.72
    OGND
    -0.60
    Hentet
    -0.59
     Administrativna
    -0.55
     ModelExpression
    -0.52
     disambiguazione
    -0.52
    AsUp
    -0.50
    Aiheesta
    -0.49
    
    -0.47
     ujednoznacz
    -0.46
    POSITIVE LOGITS
    fatalError
    0.44
    inheritdoc
    0.42
     REQU
    0.42
    findOrFail
    0.42
    throw
    0.42
    OrFail
    0.41
     Autos
    0.40
     APPROPRI
    0.40
     picioare
    0.40
     Auto
    0.40
    Activations Density 0.037%

    No Known Activations