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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 38822
    Prev
    Next
    INDEX
    Explanations

    technical terms and code structures related to programming, particularly in UI frameworks and database interactions

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

    XPath expression evaluator

    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
    (**
    -0.48
    viron
    -0.47
    setVerticalGroup
    -0.42
    vro
    -0.41
     Bohemia
    -0.41
    IRING
    -0.40
    soit
    -0.40
    Werdegang
    -0.40
    guten
    -0.39
    gerufen
    -0.39
    POSITIVE LOGITS
    XPath
    1.28
     XPath
    1.16
    ReusableCell
    1.14
    XPATH
    1.04
    imageio
    0.82
     xpath
    0.67
     JpaRepository
    0.64
    AdapterFactory
    0.61
    ImageIO
    0.57
     utafitiHapana
    0.56
    Activations Density 0.001%

    No Known Activations