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. 24-GEMMASCOPE-RES-131K
    6. 1187
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their associated roles or titles in the context of public health and social services

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

    organizations and campaigns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.81
     AssemblyCulture
    -0.61
    rrggbb
    -0.60
    AutoModerator
    -0.57
     Italijanski
    -0.56
    ImageContext
    -0.56
     nahilalakip
    -0.54
     autorytatywna
    -0.54
    GHIJKLM
    -0.54
     esternos
    -0.52
    POSITIVE LOGITS
    devServer
    0.42
     said
    0.39
     where
    0.38
    
    0.38
     mengatakan
    0.35
     жда
    0.34
     waited
    0.33
     who
    0.33
     gdzie
    0.33
     refirió
    0.33
    Activations Density 0.017%

    No Known Activations