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. 35-GEMMASCOPE-RES-16K
    6. 7433
    Prev
    Next
    INDEX
    Explanations

    terms and names related to Guyanese identity and culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.43
    ViewFeatures
    -0.42
    balleur
    -0.39
    Източници
    -0.39
    Revenir
    -0.38
     lenker
    -0.38
     ellers
    -0.38
    archiviato
    -0.37
     sozialen
    -0.36
     halla
    -0.36
    POSITIVE LOGITS
     gu
    0.90
    Gu
    0.78
     Gu
    0.78
     GU
    0.69
    gu
    0.60
     guil
    0.59
     Guilt
    0.59
    Guil
    0.59
     GUI
    0.57
     Гу
    0.56
    Activations Density 0.166%

    No Known Activations