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. 13963
    Prev
    Next
    INDEX
    Explanations

    references to councils and committees, particularly in a regulatory or governing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Zit
    -0.71
    xpos
    -0.69
     Pust
    -0.68
     impert
    -0.66
    strptime
    -0.66
     clap
    -0.66
     liturg
    -0.66
    makeText
    -0.65
    iddhar
    -0.65
    ¯¯
    -0.64
    POSITIVE LOGITS
     Council
    1.52
     councils
    1.52
     Councils
    1.46
     council
    1.43
    Council
    1.41
     COUNCIL
    1.41
    UNCIL
    1.38
    council
    1.25
    ouncil
    1.19
     Councilman
    1.00
    Activations Density 0.045%

    No Known Activations