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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15960
    Prev
    Next
    INDEX
    Explanations

    references to specific names and entities, particularly those starting with "Bu."

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

    starting with "Bu"

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    optionalTypeArgs
    -0.64
    Autoritní
    -0.55
    -------------</
    -0.49
    ?>">
    -0.48
     aranha
    -0.48
    wieś
    -0.47
    typeDefinition
    -0.47
    UnusedPrivate
    -0.45
     Biôgrafia
    -0.45
    ']))
    
    -0.45
    POSITIVE LOGITS
     Bu
    0.88
    Bu
    0.84
     BU
    0.71
     bu
    0.67
     Buxton
    0.66
    bu
    0.64
     Бу
    0.61
    Бу
    0.60
     Bucc
    0.60
    BU
    0.59
    Activations Density 0.171%

    No Known Activations