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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11629
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and operations, particularly involving sums and square roots

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marked
    -0.46
    :✨
    -0.45
    DockStyle
    -0.45
     AssemblyTitle
    -0.43
     cherchés
    -0.42
    complexContent
    -0.42
    تقاوى
    -0.42
     FetchType
    -0.41
    dafx
    -0.41
    ########.
    -0.40
    POSITIVE LOGITS
     phi
    0.47
     math
    0.45
    Попис
    0.43
     display
    0.41
     Delta
    0.41
     frac
    0.39
    cancel
    0.39
    ständige
    0.38
     Psi
    0.38
     Omega
    0.38
    Activations Density 4.227%

    No Known Activations