© 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. 70890
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    NamedQuery
    -0.33
    шое
    -0.32
     blessed
    -0.32
    QPalette
    -0.30
    webElement
    -0.30
    XtraBars
    -0.30
    setEnabled
    -0.29
     Perce
    -0.29
     clo
    -0.29
    gląd
    -0.29
    POSITIVE LOGITS
    ########.
    1.77
    :+:
    1.23
    libft
    0.96
    +#+
    0.81
     незавершена
    0.77
    rungsseite
    0.75
     ویکی‌پدی
    0.72
     nahilalakip
    0.72
    Rhestr
    0.70
    StructEnd
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.