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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122858
    Prev
    Next
    INDEX
    Explanations

    the beginning of sentences or paragraphs in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    sizeCache
    -0.58
    toMatchSnapshot
    -0.52
    orsese
    -0.50
    addPreferredGap
    -0.49
     useAppContext
    -0.48
     mauva
    -0.46
    Tikang
    -0.46
    
    -0.45
     Obrigado
    -0.45
     виправивши
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.45
    multicolumn
    0.44
    #
    0.43
    Портал
    0.39
    amp
    0.38
    SequentialGroup
    0.37
    ьаж
    0.35
     Aline
    0.35
     برانيه
    0.34
     Cassette
    0.34
    Activations Density 0.087%

    No Known Activations