© 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. 13-GEMMASCOPE-RES-16K
    11. 11658
    Prev
    Next
    INDEX
    Explanations

    references to organizations and collaborative research efforts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    GTCX
    -0.46
     LET
    -0.37
    Liebe
    -0.36
     let
    -0.35
    cesz
    -0.33
     extra
    -0.33
    Let
    -0.32
    Auf
    -0.32
     uska
    -0.32
    ùng
    -0.31
    POSITIVE LOGITS
    +:+
    0.57
    __["
    0.57
    MLLoader
    0.56
    WithIOException
    0.54
     kasarigan
    0.54
     MainAxisSize
    0.53
     defaultstate
    0.52
    OGND
    0.52
    `{.
    0.51
    +#+
    0.51
    Activations Density 1.345%

    No Known Activations