© 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. 14454
    Prev
    Next
    INDEX
    Explanations

    instances of the word "special" in various contexts

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

    "special"

    np_acts-logits-general · gemini-2.0-flash

    special leading to specific applications

    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
     huid
    -0.55
     pescoço
    -0.54
     pengend
    -0.54
     colchón
    -0.53
     keduanya
    -0.53
     vivienda
    -0.53
     cejas
    -0.53
     neumáticos
    -0.52
     mãe
    -0.52
     faldas
    -0.52
    POSITIVE LOGITS
     special
    1.23
    special
    1.21
     Special
    1.20
    Special
    1.16
     SPECIAL
    1.15
    SPECIAL
    1.06
     especial
    1.05
    pecial
    1.00
     speciale
    0.95
    especial
    0.91
    Activations Density 0.053%

    No Known Activations