© 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. 31-GEMMASCOPE-RES-16K
    11. 13641
    Prev
    Next
    INDEX
    Explanations

    terms associated with deep brain stimulation and related medical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    medical and neurological research terminology related to brain and neurodegenerative disorders.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    terminology related to neuroscience and neurological disorders, particularly brain regions, neurotransmitters, and movement disorders.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    medical and scientific terminology related to neurological disorders and brain research.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ofition
    -0.42
    Datuak
    -0.38
     ujednoznacz
    -0.37
     Vasquez
    -0.36
    bieg
    -0.36
    __":
    -0.36
    bootstrapcdn
    -0.36
    harp
    -0.35
    setVerticalGroup
    -0.35
    __":
    -0.35
    POSITIVE LOGITS
     Parkinson
    0.97
     dopamine
    0.80
     park
    0.72
     Dop
    0.71
    Park
    0.67
    Dop
    0.65
    dop
    0.64
     dop
    0.62
     PARK
    0.62
     motor
    0.60
    Activations Density 0.576%

    No Known Activations