© 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. 9-GEMMASCOPE-RES-16K
    11. 6247
    Prev
    Next
    INDEX
    Explanations

    references to the term "special" and its related contexts

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

    "special"

    np_acts-logits-general · gemini-2.0-flash

    special word usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faldas
    -0.51
     inmiddels
    -0.46
     cejas
    -0.46
    脚注の使い方
    -0.46
    setColumns
    -0.45
     portefeuille
    -0.44
    Coyote
    -0.44
     pantalón
    -0.44
    قایناق‌لار
    -0.43
     setUsername
    -0.43
    POSITIVE LOGITS
     special
    2.20
     Special
    2.09
    Special
    2.08
    special
    2.06
     SPECIAL
    1.90
    SPECIAL
    1.81
     especial
    1.65
     speciale
    1.65
    pecial
    1.60
     especiales
    1.55
    Activations Density 0.110%

    No Known Activations