© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 3389
    Prev
    Next
    INDEX
    Explanations

    code structures related to function definitions and runnable objects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     autorytatywna
    -0.54
     Rptr
    -0.45
    Dislikes
    -0.44
    inSlope
    -0.43
    MLLoader
    -0.43
     lenker
    -0.43
    IntoConstraints
    -0.42
     irony
    -0.42
     userDao
    -0.41
    Exeunt
    -0.41
    POSITIVE LOGITS
    Билгалдахарш
    0.52
    .);
    0.51
    »).
    0.50
    ++);
    0.50
    ),
    0.48
    )。
    0.48
    );
    0.47
    ]);
    0.46
    ):
    0.46
    !);
    0.46
    Activations Density 0.151%

    No Known Activations