© 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. 20-GEMMASCOPE-RES-131K
    6. 52867
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and programming syntax

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

    left parenthesis and bracket structures

    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
    rungsseite
    -0.64
    MethodManager
    -0.61
    setPointSize
    -0.61
    parsedMessage
    -0.60
    tanleria
    -0.60
    LabelTagHelper
    -0.59
    pexpr
    -0.57
    CloseOperation
    -0.57
    formik
    -0.56
    AsUp
    -0.56
    POSITIVE LOGITS
     ENJOY
    0.34
    lück
    0.32
     sneeze
    0.32
      
    0.32
    BRI
    0.31
     screws
    0.31
     catalyzed
    0.30
     pique
    0.30
    bringen
    0.29
     layers
    0.29
    Activations Density 0.092%

    No Known Activations