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. 24521
    Prev
    Next
    INDEX
    Explanations

    mentions of coding libraries and their configurations

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

    javascript and css libraries

    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
    +#+#
    -0.76
    RuleContext
    -0.72
    ScopeManager
    -0.70
    ArgumentParser
    -0.70
     propOrder
    -0.69
    CloseOperation
    -0.68
     Infórmanos
    -0.68
    AndroidJUnit
    -0.67
     StatelessWidget
    -0.66
    exitRule
    -0.66
    POSITIVE LOGITS
     gel
    0.31
     д
    0.30
     available
    0.29
     cas
    0.28
     far
    0.28
    bootstrapcdn
    0.28
     Cas
    0.28
    avanje
    0.27
     en
    0.27
     вер
    0.27
    Activations Density 0.046%

    No Known Activations