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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1863
    Prev
    Next
    INDEX
    Explanations

    specific product descriptions and details related to items, particularly crafts and utensils

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最快更新
    -0.77
    Hozzáférés
    -0.73
    dymyr
    -0.71
    AnchorStyles
    -0.66
    المكان
    -0.65
     Theſe
    -0.63
    HEET
    -0.61
    cipital
    -0.60
     tartalomajánló
    -0.60
    istered
    -0.60
    POSITIVE LOGITS
    IndentedString
    0.51
    ⓧ
    0.49
     Ebay
    0.48
     kanyang
    0.47
    assay
    0.47
     assemblage
    0.46
    InstrumentedTest
    0.46
     useCallback
    0.46
    ต้
    0.45
    Ebay
    0.45
    Activations Density 0.008%

    No Known Activations