© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 3560
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements of toxicity in relation to dietary exposure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.66
    LookAnd
    -0.48
    UnusedPrivate
    -0.46
     ModelExpression
    -0.44
    /**
    -0.43
    alib
    -0.43
    asgi
    -0.43
     melawan
    -0.41
    
    -0.40
    ızlık
    -0.40
    POSITIVE LOGITS
     exposure
    1.27
     exposures
    1.09
     Exposure
    1.09
    Exposure
    1.06
    exposure
    1.01
     EXPOSURE
    0.95
     toxicological
    0.88
     exposición
    0.86
     toxicity
    0.85
     exposed
    0.84
    Activations Density 0.670%

    No Known Activations