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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53470
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain conjunctions or prepositions

    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-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
     ویکی‌پدی
    -0.47
    parsedMessage
    -0.47
    complexContent
    -0.45
    };*/
    -0.45
     Italijanski
    -0.45
     relâche
    -0.43
    rungsseite
    -0.43
    LikeLiked
    -0.41
    +#+#
    -0.41
    Suivez
    -0.41
    POSITIVE LOGITS
    ViewFeatures
    0.48
    InjectAttribute
    0.46
    migrationBuilder
    0.44
     graag
    0.40
    
    0.39
    ValueStyle
    0.38
    RTEX
    0.38
    antMatchers
    0.37
     dress
    0.36
     दर
    0.36
    Activations Density 0.015%

    No Known Activations