© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7484
    Prev
    Next
    INDEX
    Explanations

    terms related to neurobiology and neurochemistry

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

    scientific and medical terms related to neurobiology, especially those with 'neuro-' prefixes.

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

    scientific terms related to neurology, especially prefixes like "neuro-" in medical and biological contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.68
     tslint
    -0.63
     '\\;'
    -0.59
     bookId
    -0.57
     OSError
    -0.57
     queſta
    -0.57
     مرئيه
    -0.57
     endIndex
    -0.56
     newState
    -0.56
     للاسماء
    -0.56
    POSITIVE LOGITS
     pseudo
    0.66
    Pseudo
    0.63
     Pseudo
    0.61
     electro
    0.60
     hyper
    0.59
     geo
    0.59
     photo
    0.57
     crypto
    0.57
     ultra
    0.56
     Geo
    0.56
    Activations Density 0.693%

    No Known Activations