Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 5946
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "class" and its variations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.70
     Monfieur
    -0.58
    SharedCtor
    -0.56
     للتو
    -0.56
     antiqu
    -0.55
    IndentedString
    -0.55
     iſt
    -0.54
    언
    -0.54
    WithIOException
    -0.53
     affich
    -0.52
    POSITIVE LOGITS
    Datuak
    0.82
     snippetHide
    0.70
    __":
    0.69
    adaptiveStyles
    0.68
    namespace
    0.66
    !("{}",
    0.66
    memberOf
    0.65
     ['./
    0.64
    帖最后由
    0.63
     ActionResult
    0.62
    Activations Density 0.015%

    No Known Activations