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. 39-GEMMASCOPE-RES-16K
    6. 983
    Prev
    Next
    INDEX
    Explanations

    references to polysaccharides and their variants used in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.65
     Савезне
    -0.50
     <>",
    -0.48
    saraba
    -0.43
     kaarangay
    -0.42
    Personendaten
    -0.41
    ครัว
    -0.40
     setempat
    -0.38
    RuleContext
    -0.38
     doméstico
    -0.37
    POSITIVE LOGITS
     supplement
    1.11
     supplements
    1.05
    supplement
    0.97
     supplementation
    0.93
    Supplement
    0.93
     Supplement
    0.92
     supplementing
    0.88
     capsules
    0.84
     SUPPLEMENT
    0.81
     suplemento
    0.81
    Activations Density 0.652%

    No Known Activations