© 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. 38-GEMMASCOPE-RES-16K
    11. 7557
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and varying opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.38
     Вікіпе
    -0.36
    Glej
    -0.34
    ronpa
    -0.34
    NonNull
    -0.34
    getMenuInflater
    -0.32
    IANGLES
    -0.31
     wireType
    -0.31
    Personendaten
    -0.31
     acceptez
    -0.29
    POSITIVE LOGITS
     little
    2.50
    little
    2.11
     wenig
    1.88
     few
    1.83
     weinig
    1.75
     pouco
    1.74
     LITTLE
    1.72
     very
    1.71
     мало
    1.70
    Little
    1.66
    Activations Density 1.177%

    No Known Activations