© 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. 20-GEMMASCOPE-RES-16K
    11. 7269
    Prev
    Next
    INDEX
    Explanations

    statistics and data related to baseball games and player transactions

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

    Follows punctuation marks or common contractions

    np_acts-logits-general · gemini-2.0-flash

    sports team names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isContained
    -0.76
     consultato
    -0.76
     cards
    -0.70
    mergeFrom
    -0.66
    abestanden
    -0.64
    cards
    -0.62
    awtextra
    -0.62
    AnimationsModule
    -0.61
    PYX
    -0.61
    CardModule
    -0.60
    POSITIVE LOGITS
     Oakland
    0.50
    uckles
    0.50
    Sonic
    0.49
     Sega
    0.48
     Seele
    0.48
    Sega
    0.47
     Sonic
    0.46
     AFC
    0.46
    תר
    0.45
    habil
    0.45
    Activations Density 0.170%

    No Known Activations