Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 72649
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating relationships between ideas or clauses

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

    conjunctions and lists

    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
    Lif
    -0.38
     répé
    -0.37
    explique
    -0.36
     coupable
    -0.35
    hommes
    -0.35
    不清楚
    -0.34
     habrá
    -0.34
     sûrement
    -0.34
     chré
    -0.33
     prouve
    -0.33
    POSITIVE LOGITS
     otomatig
    0.66
     disponibilités
    0.65
    bootstrapcdn
    0.62
    twimg
    0.59
    rungsseite
    0.59
    Erstellt
    0.59
     Chwiliwch
    0.59
     betweenstory
    0.56
     lenker
    0.56
    RectangleBorder
    0.56
    Activations Density 0.023%

    No Known Activations