© 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. 20-GEMMASCOPE-RES-131K
    11. 100381
    Prev
    Next
    INDEX
    Explanations

    patterns of whitespace or indentation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ProtoMessage
    -0.66
    PMailer
    -0.64
    SuppressLint
    -0.60
    IntoConstraints
    -0.60
    RTSN
    -0.59
    transQ
    -0.55
     صوتيه
    -0.53
    /**
    -0.52
    ArrowToggle
    -0.52
    EndGlobalSection
    -0.52
    POSITIVE LOGITS
    WithMany
    0.44
    getWriter
    0.40
    Whether
    0.30
    담
    0.30
    schedulers
    0.30
    whether
    0.29
     whether
    0.29
    parsedMessage
    0.28
    yfikacja
    0.28
     whose
    0.28
    Activations Density 0.009%

    No Known Activations