© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103978
    Prev
    Next
    INDEX
    Explanations

    concerns about safety and accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    دانشنامهٔ
    -0.38
     plans
    -0.37
     sle
    -0.36
    makedirs
    -0.32
    ativistic
    -0.31
    HasKey
    -0.30
     plan
    -0.30
     sen
    -0.29
     voluntarily
    -0.29
    pls
    -0.29
    POSITIVE LOGITS
    Cyfeiriadau
    0.57
    recated
    0.54
    injury
    0.48
    Hentet
    0.47
     vícti
    0.47
     دیکھیے
    0.47
     tragedia
    0.46
    rawDesc
    0.45
     injury
    0.45
     utafitiHapana
    0.45
    Activations Density 0.027%

    No Known Activations