© 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. 37-GEMMASCOPE-RES-16K
    11. 507
    Prev
    Next
    INDEX
    Explanations

    explicit language related to sexual themes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.68
     فريبيس
    -0.60
    erráneo
    -0.56
     kasarigan
    -0.50
     linkovi
    -0.50
    Rüyada
    -0.47
    帖最后由
    -0.47
    ᅠ
    -0.47
    StoreMessageInfo
    -0.46
     Wiktionnaire
    -0.46
    POSITIVE LOGITS
     bastard
    0.88
     idiot
    0.85
     scum
    0.83
     bitch
    0.80
     stupid
    0.79
     coward
    0.78
     idiots
    0.77
     filthy
    0.77
     imbec
    0.76
     ungrateful
    0.75
    Activations Density 0.343%

    No Known Activations