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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6571
    Prev
    Next
    INDEX
    Explanations

    dates and quantities related to time or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers followed by units of measurement

    np_acts-logits-general · gemini-2.0-flash

    numerical measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -0.99
     avoient
    -0.96
     enfans
    -0.94
     lèvres
    -0.93
     kvinna
    -0.85
     auroit
    -0.84
     étoient
    -0.84
     quæ
    -0.84
     prêtres
    -0.82
     ;
    -0.81
    POSITIVE LOGITS
    ish
    0.84
     ish
    0.80
     something
    0.74
     maybe
    0.73
    "....
    0.68
     or
    0.64
    "...
    0.63
    .....
    0.62
    yrs
    0.61
     yrs
    0.60
    Activations Density 0.345%

    No Known Activations