© 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. 12200
    Prev
    Next
    INDEX
    Explanations

    instances where 'somehow' or similar expressions indicate uncertainty or unexpectedness in a context

    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
    日閲覧
    -0.36
    ponible
    -0.34
    heureusement
    -0.34
    期刊论文
    -0.33
     keselamatan
    -0.33
    Referințe
    -0.33
     rétro
    -0.33
     nôtre
    -0.33
     rekan
    -0.33
    เฉ
    -0.32
    POSITIVE LOGITS
     somehow
    1.49
     Somehow
    1.41
    Somehow
    1.34
     Somewhere
    1.20
     somewhere
    1.17
    Somewhere
    1.15
    somewhere
    1.13
     Something
    1.05
    Something
    1.02
    something
    1.02
    Activations Density 0.382%

    No Known Activations