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. 23-GEMMASCOPE-RES-131K
    6. 23142
    Prev
    Next
    INDEX
    Explanations

    function call syntax in programming code

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.68
     SwitchCompat
    -0.63
    ValueStyle
    -0.58
    webElementXpaths
    -0.56
    LookAnd
    -0.55
    Cyfeiriadau
    -0.53
     SDLK
    -0.52
     ostavi
    -0.52
    sizeCache
    -0.51
     AssemblyTitle
    -0.51
    POSITIVE LOGITS
     consistente
    0.38
    ModelSerializer
    0.37
    ยนต์
    0.36
    then
    0.34
     uniquely
    0.34
    است
    0.34
     LOCATION
    0.34
     inversores
    0.34
     navegación
    0.32
    대로
    0.31
    Activations Density 0.027%

    No Known Activations