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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15782
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores or whitespace in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    devamını
    -0.46
    ſelf
    -0.46
    fici
    -0.46
     faſt
    -0.45
     lateinit
    -0.45
     itſelf
    -0.44
    (__('
    -0.44
     مشين
    -0.43
     MBC
    -0.43
     (…)
    -0.42
    POSITIVE LOGITS
     الحره
    0.57
     the
    0.56
     chegada
    0.53
     econômica
    0.51
     Económica
    0.51
     ciudadana
    0.49
     financeira
    0.48
     dulu
    0.47
     linguagem
    0.47
     myš
    0.47
    Activations Density 0.069%

    No Known Activations