Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 8639
    Prev
    Next
    INDEX
    Explanations

    code structures related to event handling and Runnable implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.83
     externi
    -0.63
    קישורים
    -0.63
    bewerken
    -0.59
     виправивши
    -0.59
     الرياضيه
    -0.58
    adaptiveStyles
    -0.58
     ostavi
    -0.57
    Identyfik
    -0.57
    Šaltiniai
    -0.55
    POSITIVE LOGITS
     actionPerformed
    0.91
    PreExecute
    0.75
    SwingConstants
    0.71
    UrlResolution
    0.71
     doInBackground
    0.70
     MainAxisSize
    0.65
     objectAtIndex
    0.63
    HostException
    0.61
    раздо
    0.60
    VersionUID
    0.60
    Activations Density 0.031%

    No Known Activations