© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 10838
    Prev
    Next
    INDEX
    Explanations

    references to software tools and libraries related to programming and development

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

    android code snippets and words

    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
     boneca
    -0.34
     diras
    -0.33
     pudesse
    -0.33
     esfuerzos
    -0.33
     "..\..\
    -0.31
    dagangan
    -0.30
     hendes
    -0.30
     bocetos
    -0.29
     suaminya
    -0.29
     demikian
    -0.28
    POSITIVE LOGITS
    AndEndTag
    0.80
    ChrTalk
    0.77
     betweenstory
    0.75
     noDo
    0.73
     utafitiHapana
    0.69
     ब्रेकडाउन
    0.64
    expandindo
    0.64
    tangentMode
    0.62
    RectangleBorder
    0.62
    GIVEREF
    0.61
    Activations Density 0.133%

    No Known Activations