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. 92128
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols indicating lists or sections

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

    news and company names

    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
    oplayer
    -0.60
     uſed
    -0.58
    endphp
    -0.58
     resourceCulture
    -0.57
     queſta
    -0.57
     mijne
    -0.56
     faſt
    -0.54
    lapsingToolbar
    -0.54
    новништво
    -0.53
     jsPsych
    -0.52
    POSITIVE LOGITS
    ñores
    0.55
    
    0.41
     Conley
    0.38
    而
    0.38
    Aholisi
    0.38
    Aviso
    0.36
     Innenstadt
    0.36
     Abends
    0.36
    省市镇
    0.36
     міста
    0.35
    Activations Density 0.000%

    No Known Activations