© 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. 20-GEMMASCOPE-RES-16K
    11. 4809
    Prev
    Next
    INDEX
    Explanations

    scientific discussions related to chemical processes and biological systems

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

    scientific research methodology and detailed scientific study descriptions, particularly focusing on data analysis, research teams, and research findings.

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

    This neuron detects paragraphs that begin with scientific findings, particularly focusing on when researchers or scientists report new discoveries or observations.

    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
    routeProvider
    -0.39
     ho
    -0.31
     iż
    -0.30
     class
    -0.29
    standes
    -0.29
    class
    -0.28
     merely
    -0.28
     and
    -0.28
    addr
    -0.28
     the
    -0.27
    POSITIVE LOGITS
     researchers
    0.66
     חיצוניים
    0.60
     Researchers
    0.59
    AddTagHelper
    0.59
     invokingState
    0.58
    ScopeManager
    0.57
     indisponible
    0.57
    Researchers
    0.55
     فريبيس
    0.54
     greateſt
    0.54
    Activations Density 0.366%

    No Known Activations