© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 108063
    Prev
    Next
    INDEX
    Explanations

    elements and attributes in code structures, particularly related to layout and command groups

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

    acr commands and code snippets

    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
    ductos
    -0.39
    writeFieldEnd
    -0.37
    RetentionPolicy
    -0.35
     Wahrnehmung
    -0.35
     Kreise
    -0.33
    UrlResolution
    -0.33
     ventre
    -0.33
     createState
    -0.33
     trône
    -0.33
    +#+#
    -0.32
    POSITIVE LOGITS
    WebServlet
    0.59
    الحياه
    0.57
    UnknownFields
    0.52
    UnknownFieldSet
    0.51
     ISNI
    0.51
     StatefulWidget
    0.51
    ExtendWith
    0.50
    TagMode
    0.50
    |}{$
    0.48
    StartTag
    0.48
    Activations Density 0.019%

    No Known Activations