© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 119834
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their effects on the nervous system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     typelib
    -0.67
    évaluateur
    -0.63
     оригіналу
    -0.63
     فريبيس
    -0.63
     Chwiliwch
    -0.61
     estekak
    -0.61
     ExecuteAsync
    -0.59
    ValueStyle
    -0.59
    ensement
    -0.57
    IntoConstraints
    -0.57
    POSITIVE LOGITS
    package
    0.36
     package
    0.32
    Dave
    0.31
     mel
    0.31
     lives
    0.31
    Pre
    0.29
     tratando
    0.29
    iken
    0.28
     safe
    0.28
     Dave
    0.28
    Activations Density 0.141%

    No Known Activations