© 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. 6798
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or qualifiers in statements

    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
     Normdatei
    -0.73
    RegressionTest
    -0.66
     Infórmanos
    -0.65
     queſta
    -0.65
     Lightboxes
    -0.63
     Roskov
    -0.63
    Попис
    -0.59
     nakalista
    -0.59
     raiſ
    -0.58
     ModelExpression
    -0.57
    POSITIVE LOGITS
    ,
    0.36
     Daß
    0.33
    看好
    0.33
     THIS
    0.33
     resourceCulture
    0.32
     WITHOUT
    0.32
     pierna
    0.32
     sabido
    0.32
     Krieger
    0.32
     INCLUDES
    0.32
    Activations Density 0.524%

    No Known Activations