© 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. 15835
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or hesitation in language

    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
    жнему
    -0.45
    complexContent
    -0.42
    CppMethod
    -0.40
    ormous
    -0.40
    Hostel
    -0.38
    pulumi
    -0.38
     fieldNum
    -0.38
     ***!
    -0.37
    mitive
    -0.37
     total
    -0.36
    POSITIVE LOGITS
     maybe
    1.37
     Maybe
    1.34
    Maybe
    1.32
    maybe
    1.29
    perhaps
    1.28
     Perhaps
    1.27
     perhaps
    1.27
    Perhaps
    1.20
    anskje
    1.06
     Vielleicht
    1.00
    Activations Density 0.320%

    No Known Activations