© 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. 7871
    Prev
    Next
    INDEX
    Explanations

    C code structure and syntax elements related to device drivers

    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
     sachet
    -0.42
    pushFollow
    -0.37
    льше
    -0.36
     induction
    -0.36
     maso
    -0.35
     neceff
    -0.35
     accum
    -0.34
     serangga
    -0.34
     Trail
    -0.34
     Cag
    -0.34
    POSITIVE LOGITS
     device
    0.82
     physical
    0.79
     devices
    0.78
     Physical
    0.76
     hardware
    0.74
     Device
    0.74
    デバイス
    0.71
     Devices
    0.71
    physical
    0.71
    Physical
    0.69
    Activations Density 1.195%

    No Known Activations