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. 32-GEMMASCOPE-RES-131K
    6. 129939
    Prev
    Next
    INDEX
    Explanations

    references to package management and environment configurations in software development

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

    configuration files and package managers

    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_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.47
    fjspx
    -0.43
    ContextHolder
    -0.41
    endphp
    -0.40
    ///</
    -0.37
    detectChanges
    -0.35
     ddelweddau
    -0.34
    urb
    -0.34
     mo
    -0.34
     Mog
    -0.33
    POSITIVE LOGITS
     conda
    0.71
    conda
    0.60
     فريبيس
    0.59
     Anaconda
    0.56
     argint
    0.56
    aconda
    0.54
     desierto
    0.50
     miniaturka
    0.50
    Activation
    0.47
     ſtate
    0.47
    Activations Density 0.007%

    No Known Activations