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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 68787
    Prev
    Next
    INDEX
    Explanations

    references to artistic or creative projects

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

    studio photoshoots and scripts

    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
    typeorm
    -0.30
    MergeFrom
    -0.30
    IntoConstraints
    -0.29
    JpaRepository
    -0.29
    Sure
    -0.28
    DockStyle
    -0.28
     Política
    -0.27
     granat
    -0.27
    CrossRef
    -0.27
    TRAILING
    -0.26
    POSITIVE LOGITS
    ագրություններ
    0.70
     otomatig
    0.67
     musicals
    0.65
     comedy
    0.65
    ьаж
    0.63
    رشف
    0.63
     entertainments
    0.63
     movie
    0.63
     Geſch
    0.62
     entertainment
    0.60
    Activations Density 0.209%

    No Known Activations