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. 75351
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and concepts related to genetics and molecular biology

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

    technical terms and foreign words

    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
    AddTagHelper
    -0.82
    WebVitals
    -0.77
    WillAppear
    -0.68
    interopRequire
    -0.63
    帖最后由
    -0.60
    httphttps
    -0.60
     BorderRadius
    -0.58
    AsUp
    -0.57
     HasFactory
    -0.57
    invokeLater
    -0.56
    POSITIVE LOGITS
    mawia
    0.37
     aulas
    0.37
     circling
    0.37
    yorsunuz
    0.36
     coches
    0.35
     reír
    0.35
    มอง
    0.34
     chão
    0.34
     paño
    0.34
     cepillo
    0.34
    Activations Density 0.180%

    No Known Activations