© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 7612
    Prev
    Next
    INDEX
    Explanations

    specific terms related to cellular biology and experimental conditions

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

    Following a treatment or exposure

    np_acts-logits-general · gemini-2.0-flash

    following exposure or treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abestanden
    -0.57
    емости
    -0.57
    емость
    -0.57
    zerland
    -0.50
     savez
    -0.49
    sivité
    -0.49
    endphp
    -0.49
    Throwaway
    -0.48
    AspectRatio
    -0.48
    mappedBy
    -0.47
    POSITIVE LOGITS
     exposure
    1.33
     treatment
    1.17
     treatments
    1.13
    exposure
    1.09
     Exposure
    1.05
     exposures
    1.04
    Exposure
    1.01
    treatment
    0.96
     exposing
    0.95
     Treatments
    0.93
    Activations Density 2.571%

    No Known Activations