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. 33-GEMMASCOPE-RES-131K
    6. 65807
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements, particularly related to object definitions and exports

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.71
    tagHelperRunner
    -0.69
    PerformLayout
    -0.68
    MLLoader
    -0.65
     finalmente
    -0.62
     finally
    -0.60
     Finally
    -0.59
    новниш
    -0.56
     val
    -0.56
    يكب
    -0.55
    POSITIVE LOGITS
     let
    0.91
    let
    0.77
     Let
    0.68
    Let
    0.68
     пусть
    0.66
     letting
    0.52
    LET
    0.49
     LET
    0.47
    styleType
    0.47
     lets
    0.45
    Activations Density 0.013%

    No Known Activations