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. 65826
    Prev
    Next
    INDEX
    Explanations

    keywords related to API operations for managing resources

    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
    parsedMessage
    -0.66
    webElementGuid
    -0.58
     تضيفلها
    -0.57
    AddTagHelper
    -0.57
    SourceChecksum
    -0.56
    
    -0.56
    最快更新
    -0.56
     Wikimedijinoj
    -0.55
    )++;
    -0.53
    ➟
    -0.53
    POSITIVE LOGITS
     elő
    0.36
    Async
    0.33
    TintMode
    0.33
     Fog
    0.32
    Via
    0.32
    Raw
    0.31
    insics
    0.30
    PostExecute
    0.30
    Validator
    0.30
    Gold
    0.30
    Activations Density 0.026%

    No Known Activations