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. 61810
    Prev
    Next
    INDEX
    Explanations

    geographical features, particularly bodies of water and their surrounding areas

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

    bodies of water

    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
    Życiorys
    -0.47
    IBOutlet
    -0.43
     disambiguazione
    -0.40
     Igreja
    -0.36
    //
    -0.35
     мәгълү
    -0.35
     clinic
    -0.35
     parseFrom
    -0.35
     Fernandez
    -0.33
     pitch
    -0.32
    POSITIVE LOGITS
     ModelExpression
    0.67
     autorytatywna
    0.67
     kasarigan
    0.52
     MainAxisSize
    0.50
    المشاركات
    0.49
    Comté
    0.49
    erráneo
    0.48
     للاسماء
    0.48
     fleuve
    0.47
    bootstrapcdn
    0.47
    Activations Density 0.019%

    No Known Activations