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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101468
    Prev
    Next
    INDEX
    Explanations

    elements of mathematical notation, particularly related to expressions and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    beeld
    -0.39
    맑
    -0.33
     verzorg
    -0.32
     пла
    -0.31
    matta
    -0.30
     bezig
    -0.30
    ngrx
    -0.29
    FTFY
    -0.29
     Mitteln
    -0.29
     Consultez
    -0.29
    POSITIVE LOGITS
     الحره
    0.76
    GEBURTSDATUM
    0.74
    Personendaten
    0.65
     initComponents
    0.63
    Hentet
    0.61
    fileID
    0.59
    posedge
    0.59
    Diweddarwch
    0.58
    AndEndTag
    0.56
    帖最后由
    0.56
    Activations Density 0.001%

    No Known Activations