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. 13-GEMMASCOPE-RES-16K
    6. 55
    Prev
    Next
    INDEX
    Explanations

    expressions involving list operations and transformations in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming functions or methods related to list and map operations.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.76
    !("{
    -0.73
    awtextra
    -0.71
     BorderRadius
    -0.70
    UnusedPrivate
    -0.66
     Waray
    -0.66
    WriteBarrier
    -0.65
     OMITBAD
    -0.65
    writeFieldEnd
    -0.64
    Rohy
    -0.64
    POSITIVE LOGITS
    <thead>
    0.66
    Linq
    0.58
    map
    0.57
     Catalytic
    0.57
    Collectors
    0.56
    `);
    0.54
     fonction
    0.51
     africain
    0.51
     asiatique
    0.51
    Factory
    0.51
    Activations Density 0.065%

    No Known Activations