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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 65718
    Prev
    Next
    INDEX
    Explanations

    prepositions and their frequency in the text

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

    molecular, collective, coverage, maximal, degeneracy, cores

    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
    You
    -0.33
    I
    -0.31
     that
    -0.31
     you
    -0.30
    you
    -0.28
    .
    -0.28
    <strong>
    -0.27
    t
    -0.27
    n
    -0.27
     followed
    -0.26
    POSITIVE LOGITS
     Administrativna
    1.09
    parsedMessage
    1.05
     ivelany
    1.03
     linkovi
    1.00
     Italijani
    0.95
     informée
    0.94
    Vidite
    0.93
    rungsseite
    0.93
    ніципалі
    0.92
     Италијани
    0.91
    Activations Density 0.121%

    No Known Activations