© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102932
    Prev
    Next
    INDEX
    Explanations

    code-like structures or syntax, particularly involving string manipulation or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    AndEndTag
    -0.62
     ſch
    -0.58
     Reſ
    -0.57
    setVerticalGroup
    -0.55
    tangentMode
    -0.55
    awtextra
    -0.54
    WebMethod
    -0.54
     estekak
    -0.53
    outWeight
    -0.53
     autorytatywna
    -0.53
    POSITIVE LOGITS
     تضيفلها
    0.43
    Pranala
    0.42
    ísimas
    0.41
    ädchen
    0.39
     toată
    0.37
    ctivos
    0.34
    ERVIS
    0.34
    édie
    0.33
    rboles
    0.32
     picioare
    0.32
    Activations Density 0.249%

    No Known Activations