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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15716
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quality assessment or performance levels

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     ब्रेकडाउन
    -0.79
    ⟬
    -0.73
     surla
    -0.61
    帖最后由
    -0.56
    SequentialGroup
    -0.56
     Мексичка
    -0.56
    hoea
    -0.55
    dafx
    -0.54
    ElementException
    -0.53
    pirable
    -0.53
    POSITIVE LOGITS
     conformément
    0.40
     yoktur
    0.40
     recomendaciones
    0.38
     préfé
    0.38
     mejoras
    0.37
     importado
    0.37
     spoluprá
    0.37
     importar
    0.37
     aprovecha
    0.37
     vyst
    0.37
    Activations Density 0.899%

    No Known Activations