© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10648
    Prev
    Next
    INDEX
    Explanations

    references to characters in narratives or storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.96
     myſelf
    -0.87
     faſt
    -0.84
    Tipp
    -0.80
     againſt
    -0.76
     impunity
    -0.75
     Monfieur
    -0.75
    uesday
    -0.73
     Duca
    -0.73
     setOpen
    -0.73
    POSITIVE LOGITS
     character
    2.70
     characters
    2.50
     Character
    2.37
    character
    2.32
     CHARACTER
    2.27
    characters
    2.17
    Character
    2.15
     Characters
    2.15
    Characters
    1.91
     karakter
    1.85
    Activations Density 0.070%

    No Known Activations