© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 11666
    Prev
    Next
    INDEX
    Explanations

    sentences that express doubt or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginInit
    -0.61
    parsedMessage
    -0.60
    RenderAtEndOf
    -0.58
    참고
    -0.58
    ándolos
    -0.56
    parseFrom
    -0.55
     kasarigan
    -0.54
    TintMode
    -0.54
    prüche
    -0.53
    Zeneca
    -0.53
    POSITIVE LOGITS
     about
    3.88
    about
    2.65
     ABOUT
    2.31
    About
    2.28
     About
    2.15
     tentang
    2.12
     abt
    1.77
     apie
    1.73
    ABOUT
    1.65
    bout
    1.65
    Activations Density 1.099%

    No Known Activations