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. 65784
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements, particularly related to generics and types

    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
     >=",
    -0.59
     '\\;'
    -0.54
     <=",
    -0.47
    rrggbb
    -0.47
    PostExecute
    -0.45
    Ecotoxicity
    -0.45
    Diweddarwch
    -0.43
    invokeLater
    -0.43
    XtraGrid
    -0.43
    __*/
    -0.40
    POSITIVE LOGITS
     first
    1.70
    first
    1.34
     FIRST
    1.20
     primeiro
    1.18
    第一个
    1.17
    第一
    1.16
     pertama
    1.16
     primero
    1.13
     primeira
    1.13
     første
    1.13
    Activations Density 0.105%

    No Known Activations