© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 15720
    Prev
    Next
    INDEX
    Explanations

    occurrences of event listener functions and document type declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.87
    ftagPool
    -0.77
    WEBPACK
    -0.76
     PeEnEo
    -0.72
     ExecuteAsync
    -0.72
     الحره
    -0.70
     heapq
    -0.70
    URLException
    -0.68
    󠁿
    -0.68
     Ork
    -0.67
    POSITIVE LOGITS
    addEventListener
    1.15
    CodeAttribute
    1.00
     Initialized
    0.83
    makeText
    0.82
    texttt
    0.69
    RestController
    0.68
    EventListener
    0.64
    maketitle
    0.63
    Referências
    0.61
    addCriterion
    0.59
    Activations Density 0.019%

    No Known Activations