© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14395
    Prev
    Next
    INDEX
    Explanations

    references to classic or traditional concepts, items, or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "classic"

    np_acts-logits-general · gemini-2.0-flash

    classic example / style / feel

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     FontWeight
    -0.46
     RouterModule
    -0.45
     Tangerang
    -0.42
     Humber
    -0.42
     FormsModule
    -0.41
     Fur
    -0.41
    fahr
    -0.39
     Autorisations
    -0.39
    iotensin
    -0.39
    imeo
    -0.38
    POSITIVE LOGITS
     classic
    1.23
    classic
    1.20
    Classic
    1.11
     CLASSIC
    1.09
     Classic
    1.09
     clássico
    0.98
     klasik
    0.97
     classiques
    0.97
     clásico
    0.94
     classique
    0.93
    Activations Density 0.123%

    No Known Activations