© 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. 3-GEMMASCOPE-RES-16K
    11. 6083
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental and health-related impacts of substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charms
    -0.38
     тор
    -0.35
    turnstile
    -0.35
     MainAxisSize
    -0.35
    getDoctrine
    -0.34
     Walkover
    -0.34
     оча
    -0.33
    toPromise
    -0.32
    kheim
    -0.32
    Bored
    -0.32
    POSITIVE LOGITS
     pastor
    0.66
    ato
    0.63
    ef
    0.61
     فريبيس
    0.60
    Pastor
    0.59
     Pastor
    0.59
    awtextra
    0.58
    Xna
    0.57
    ATO
    0.54
     tale
    0.54
    Activations Density 1.411%

    No Known Activations