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. 29435
    Prev
    Next
    INDEX
    Explanations

    expressions of hope, ambition, and plans related to business and market strategies

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

    action verbs and intentions

    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
    ossed
    -0.32
    Progress
    -0.31
    COLE
    -0.29
     mengh
    -0.29
    }');
    -0.29
     AssemblyCulture
    -0.28
     jaki
    -0.28
     Ressources
    -0.28
    lente
    -0.28
     fluores
    -0.28
    POSITIVE LOGITS
     للاسماء
    0.70
     surla
    0.69
     Signalez
    0.68
    adaptiveStyles
    0.68
     kaarangay
    0.66
    enderror
    0.65
     <<<<<<<<<<<<<<
    0.63
    sizeCache
    0.61
    +#+#
    0.60
    argout
    0.60
    Activations Density 0.024%

    No Known Activations