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. 22-GEMMASCOPE-RES-16K
    6. 14942
    Prev
    Next
    INDEX
    Explanations

    nutritional information about food ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.54
    enumii
    -0.46
    
    -0.45
     initComponents
    -0.44
     "..\..\..\
    -0.42
     Beur
    -0.41
     restricted
    -0.41
     dto
    -0.40
    ษัท
    -0.40
     disappointed
    -0.40
    POSITIVE LOGITS
     antioxidants
    0.50
     nutrients
    0.49
    OGND
    0.46
     antioxidant
    0.45
     unique
    0.44
    styleType
    0.44
     richness
    0.42
    unique
    0.41
     rich
    0.40
    丰富的
    0.40
    Activations Density 0.138%

    No Known Activations