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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4485
    Prev
    Next
    INDEX
    Explanations

    elements related to actions or processes of verification and confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gear
    -0.37
     Gems
    -0.34
     vej
    -0.32
     عج
    -0.31
     Gem
    -0.31
     Spiral
    -0.31
    archiviato
    -0.31
     Bert
    -0.31
     Kamb
    -0.31
     kn
    -0.31
    POSITIVE LOGITS
    AsUp
    0.68
    HideFlags
    0.65
     mergeFrom
    0.62
     Autorizaciones
    0.56
    Hentet
    0.54
    RTEE
    0.52
    pingente
    0.51
    RenderAtEndOf
    0.51
    íncia
    0.51
     мәкал
    0.49
    Activations Density 0.112%

    No Known Activations