© 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. 20-GEMMASCOPE-RES-16K
    11. 14759
    Prev
    Next
    INDEX
    Explanations

    phrases indicating examples or specifications

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

    "as" (or similar words) followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    introducing lists of examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XNUMX
    -0.62
    ValueStyle
    -0.60
    Carriera
    -0.59
    UnusedPrivate
    -0.57
     båda
    -0.56
     ſame
    -0.55
    contentPane
    -0.54
     незавершена
    -0.54
     насељу
    -0.53
    ContentAsync
    -0.53
    POSITIVE LOGITS
     those
    1.52
    those
    1.25
    :
    1.10
     Those
    1.04
     ones
    0.99
     namely
    0.98
    Those
    0.98
    namely
    0.96
     celles
    0.93
     THOSE
    0.88
    Activations Density 0.445%

    No Known Activations