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. 129996
    Prev
    Next
    INDEX
    Explanations

    programming concepts related to logging and error handling

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

    static final Logger

    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
    出版年
    -0.53
    ModelAdmin
    -0.49
    adaptiveStyles
    -0.45
     EClass
    -0.42
    devamını
    -0.42
    OGND
    -0.40
     noDo
    -0.39
    fjspx
    -0.38
    routeProvider
    -0.38
     ModelExpression
    -0.38
    POSITIVE LOGITS
     log
    1.77
     logger
    1.72
    logger
    1.66
     Log
    1.56
     logging
    1.55
     Logger
    1.55
     logs
    1.55
    log
    1.55
     LOG
    1.47
     Logging
    1.42
    Activations Density 0.045%

    No Known Activations