© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 13733
    Prev
    Next
    INDEX
    Explanations

    references to master and book components in a coding context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    WriteBarrier
    -0.59
     Far
    -0.55
     U
    -0.55
    .,
    -0.54
     he
    -0.53
    はじめに
    -0.53
    gmail
    -0.53
    ///</
    -0.52
     “
    -0.51
     Med
    -0.51
    POSITIVE LOGITS
    _
    2.05
    \_
    1.04
     Theſe
    0.92
     Shakspeare
    0.86
     Monfieur
    0.84
     Efq
    0.80
    _{
    0.78
     Anſ
    0.76
     Eſ
    0.75
     Beſ
    0.74
    Activations Density 0.664%

    No Known Activations