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. 27-GEMMASCOPE-RES-16K
    6. 9740
    Prev
    Next
    INDEX
    Explanations

    terms related to commercial activities and interests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drž
    -0.50
     daarbij
    -0.50
     čast
    -0.50
     onderdeel
    -0.48
     hoogte
    -0.47
    sunflower
    -0.47
    AccessLevel
    -0.47
     temperatuur
    -0.46
     aproape
    -0.46
     voed
    -0.46
    POSITIVE LOGITS
     Chwiliwch
    0.62
    expandindo
    0.59
     deal
    0.56
     Trade
    0.56
     Deal
    0.54
     дописавши
    0.53
     DEAL
    0.52
    deal
    0.51
     Negotiation
    0.50
     Deals
    0.49
    Activations Density 0.238%

    No Known Activations