© 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
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 11870
    Prev
    Next
    INDEX
    Explanations

    instances of exposure or revealing something, particularly in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Benzema
    -0.30
     Hotspur
    -0.30
    andalf
    -0.30
    itrile
    -0.28
     dépos
    -0.28
     tiens
    -0.28
     établie
    -0.27
    InBytes
    -0.27
    zonych
    -0.26
    杯
    -0.26
    POSITIVE LOGITS
    exposed
    0.83
    Хьажоргаш
    0.80
     exposed
    0.80
    Exposed
    0.76
     exposing
    0.75
     Exposed
    0.74
    露出
    0.73
     uncovered
    0.71
     bare
    0.70
    expose
    0.69
    Activations Density 0.554%

    No Known Activations