© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4810
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts indicating suitability or fittingness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
     Stoner
    -0.90
     وتسجيلات
    -0.89
     albedo
    -0.88
     OFDb
    -0.84
    wiſe
    -0.82
    esterday
    -0.80
     Efq
    -0.80
     moons
    -0.80
    pædia
    -0.79
    Negro
    -0.79
    POSITIVE LOGITS
    fit
    1.60
     FIT
    1.59
     fit
    1.54
     Fit
    1.51
    Fit
    1.50
     fits
    1.48
     Fits
    1.48
    FIT
    1.41
    Fits
    1.38
     Fitz
    1.33
    Activations Density 0.052%

    No Known Activations