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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 56690
    Prev
    Next
    INDEX
    Explanations

    words related to medical and biological conditions

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

    cy or Kush compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    principalColumn
    -0.41
     Vainqueur
    -0.36
    abestanden
    -0.35
    Únete
    -0.34
     regalías
    -0.34
     geblieben
    -0.34
     polski
    -0.34
     ejemplares
    -0.33
     Verkehr
    -0.32
    oggi
    -0.32
    POSITIVE LOGITS
     AssemblyCulture
    0.81
     EconPapers
    0.77
    AndEndTag
    0.69
    ftagPool
    0.68
    rungsseite
    0.66
    hyrchwyd
    0.66
    AddTagHelper
    0.65
     FontWeight
    0.65
     ब्रेकडाउन
    0.64
    AutoScaleMode
    0.63
    Activations Density 0.165%

    No Known Activations