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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2292
    Prev
    Next
    INDEX
    Explanations

    references to ComVisible attributes in assembly metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.06
    matchCondition
    -0.87
    клопе
    -0.75
    참고
    -0.74
    AnchorStyles
    -0.72
    addCriterion
    -0.64
    stateMutability
    -0.64
     QtCore
    -0.63
    expandindo
    -0.63
     שוליים
    -0.62
    POSITIVE LOGITS
    CodeDom
    1.62
     ComVisible
    1.24
    ExecutionContext
    1.00
    PREFERRED
    0.68
    appcompat
    0.55
    νομ
    0.54
    StoreMessageInfo
    0.51
    /***/
    0.51
    PRNewswire
    0.49
     conci
    0.49
    Activations Density 0.006%

    No Known Activations