© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1471
    Prev
    Next
    INDEX
    Explanations

    mentions of "Ba" or "BA" and related terms associated with "shark."

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

    Follows "Ba" or contains "Ba(OH)~2~"

    np_acts-logits-general · gemini-2.0-flash

    Bauman, Bahamas, Ba(OH)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    뀜
    -0.61
    cookieParser
    -0.52
     Presentations
    -0.52
    ollectionView
    -0.48
    뀔
    -0.47
    awtextra
    -0.45
    뀐
    -0.45
     bandas
    -0.45
     Presentation
    -0.45
     IActionResult
    -0.45
    POSITIVE LOGITS
     disambiguazione
    0.83
     Ba
    0.73
    hadur
    0.72
     endwhile
    0.68
    RetentionPolicy
    0.68
     BAH
    0.65
    Ba
    0.64
    pyrene
    0.64
    tvguidetime
    0.64
    tangentMode
    0.64
    Activations Density 0.076%

    No Known Activations