Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15823
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmaceuticals and scientific publications

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Erbe
    -0.84
     Raub
    -0.78
     Mangel
    -0.78
     Erben
    -0.75
     Insel
    -0.73
     Westen
    -0.71
     Krone
    -0.69
     Mutter
    -0.69
     Arzt
    -0.69
     Herzen
    -0.68
    POSITIVE LOGITS
    friger
    0.70
     verantwoorde
    0.69
    ésult
    0.69
     maș
    0.68
    iſten
    0.67
     فريبيس
    0.63
     vrijwilli
    0.63
    unicip
    0.62
     vlieg
    0.62
    eronau
    0.60
    Activations Density 2.108%

    No Known Activations