© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7745
    Prev
    Next
    INDEX
    Explanations

    specific names or references related to the figure Roy

    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
    ViewImports
    -0.56
     fhew
    -0.52
     mostrarán
    -0.47
    qvarna
    -0.47
     poète
    -0.46
    ništ
    -0.45
     encargado
    -0.45
    Jeografia
    -0.45
    windowFixed
    -0.45
    )_/¯
    -0.44
    POSITIVE LOGITS
     Boy
    0.58
    Boy
    0.57
     Joy
    0.54
    Roy
    0.52
    roy
    0.51
    oy
    0.50
     Toy
    0.49
    Joy
    0.49
     Roy
    0.49
    OY
    0.49
    Activations Density 0.126%

    No Known Activations