© 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. 12-GEMMASCOPE-RES-16K
    11. 4514
    Prev
    Next
    INDEX
    Explanations

    terms related to health conditions and treatments in a medical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Erbe
    -0.79
     Erben
    -0.76
     Strahl
    -0.72
     Raub
    -0.71
     Mangel
    -0.71
     Verband
    -0.70
     Erde
    -0.68
     Herzen
    -0.68
     Nadel
    -0.67
    Portail
    -0.67
    POSITIVE LOGITS
     فريبيس
    0.63
    dirond
    0.60
    ésult
    0.55
    friger
    0.54
     maș
    0.51
     vlieg
    0.50
    плек
    0.48
     verantwoorde
    0.47
     werkzaam
    0.47
    unicip
    0.47
    Activations Density 3.855%

    No Known Activations