© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7576
    Prev
    Next
    INDEX
    Explanations

    information related to medicinal benefits and components of dietary supplements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.52
    httphttps
    -0.45
     oprot
    -0.44
     sarili
    -0.44
     simplifié
    -0.43
    CppMethod
    -0.43
     Empieza
    -0.42
    makeConstraints
    -0.41
    Hozzáférés
    -0.41
    numerusform
    -0.40
    POSITIVE LOGITS
     relieves
    0.88
     relieve
    0.87
     improves
    0.87
     reduces
    0.86
     reduce
    0.85
     Reduces
    0.82
     improve
    0.82
     Improves
    0.81
     promotes
    0.79
    Reduces
    0.79
    Activations Density 0.589%

    No Known Activations