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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 70654
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and measurements within experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     للاسماء
    -0.66
    riwal
    -0.53
    styleType
    -0.50
    الحياه
    -0.43
     actionBar
    -0.42
     Enough
    -0.39
    fantasy
    -0.38
    hoeddwyd
    -0.37
    WriteLiteral
    -0.37
    
    
    -0.36
    POSITIVE LOGITS
     للمعارف
    0.57
    enderror
    0.50
     beroep
    0.43
     rise
    0.41
     przep
    0.41
     BoxFit
    0.41
     MainAxisSize
    0.40
    WebpackPlugin
    0.39
    AddTagHelper
    0.39
    GetAxis
    0.38
    Activations Density 0.100%

    No Known Activations