Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 92698
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court decisions

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

    affirm or denied

    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
     Saba
    -0.36
    thenReturn
    -0.36
     abar
    -0.34
    stateProvider
    -0.34
     Boch
    -0.34
     reels
    -0.34
    setList
    -0.34
    ziali
    -0.33
    Véxase
    -0.33
    isLoggedIn
    -0.33
    POSITIVE LOGITS
    UrlResolution
    0.61
    unref
    0.55
    SharedCtor
    0.51
    featureID
    0.51
     contextLoads
    0.50
    ьаж
    0.50
    andExpect
    0.49
     ***!
    0.49
     مرئيه
    0.48
    JspWriter
    0.48
    Activations Density 0.142%

    No Known Activations