© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11973
    Prev
    Next
    INDEX
    Explanations

    articles in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "A" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    a followed by word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     inſ
    -0.52
     deſt
    -0.47
     themſelves
    -0.45
     becauſe
    -0.44
     itſelf
    -0.42
     faſt
    -0.42
    endregion
    -0.41
     ſhe
    -0.40
     juſ
    -0.40
     ſever
    -0.39
    POSITIVE LOGITS
     nicer
    0.72
     crappy
    0.71
     nice
    0.70
     shitty
    0.69
     darn
    0.68
     guy
    0.68
     bit
    0.68
     HUGE
    0.65
     few
    0.65
    nice
    0.63
    Activations Density 0.385%

    No Known Activations