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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 24535
    Prev
    Next
    INDEX
    Explanations

    topics related to medical treatments and their parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    étaro
    -0.35
     sappi
    -0.34
     investors
    -0.34
    Dés
    -0.33
    врат
    -0.33
    ดิ
    -0.32
     eat
    -0.32
     readers
    -0.32
     ultimate
    -0.31
    Descripció
    -0.31
    POSITIVE LOGITS
    parsedMessage
    0.67
     Majefty
    0.57
     Sauna
    0.56
    ſelf
    0.56
     linkovi
    0.56
     modality
    0.52
     Therapist
    0.52
    EDEFAULT
    0.51
     ProgressDialog
    0.51
    astify
    0.50
    Activations Density 0.024%

    No Known Activations