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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 105142
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to discussions or processes

    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
     disambiguazione
    -0.86
    ьаж
    -0.80
     Numerade
    -0.77
    الإنجليزية
    -0.76
    rungsseite
    -0.75
     gynhyrchwyd
    -0.73
     estekak
    -0.73
     queſta
    -0.71
    tangentMode
    -0.71
    ंदीखरीदारी
    -0.70
    POSITIVE LOGITS
    .*")]
    0.35
     Bapak
    0.29
    lrrrr
    0.27
     Formación
    0.27
     Ein
    0.27
    难
    0.27
     venido
    0.27
    getNext
    0.27
    ther
    0.26
     Relaciones
    0.26
    Activations Density 0.005%

    No Known Activations