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. 7417
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation and syntax elements commonly used in programming and code representation

    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
    Enllaces
    -0.63
    toe
    -0.61
    Externí
    -0.56
     top
    -0.55
     toe
    -0.53
     “
    -0.52
    onHide
    -0.50
    orang
    -0.50
     gene
    -0.49
    getDrawable
    -0.49
    POSITIVE LOGITS
    UnknownFieldSet
    0.91
    SourceChecksum
    0.88
    AndEndTag
    0.80
     linkovi
    0.76
    parametrize
    0.71
    ByVersion
    0.69
     flyknit
    0.69
    InjectAttribute
    0.69
    }){
    0.68
     '{@
    0.68
    Activations Density 0.067%

    No Known Activations