© 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. 13849
    Prev
    Next
    INDEX
    Explanations

    content related to written communication, such as letters and correspondence

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.53
    createCanvas
    -0.51
     createSprite
    -0.49
    spre
    -0.48
     Signalez
    -0.46
    zyg
    -0.45
    DECREF
    -0.43
    ouds
    -0.43
    }],
    -0.43
    atase
    -0.41
    POSITIVE LOGITS
     letter
    3.35
     letters
    2.90
    letter
    2.78
     Letter
    2.71
    Letter
    2.67
     LETTER
    2.62
     Letters
    2.47
     lettre
    2.40
    letters
    2.39
    LETTER
    2.37
    Activations Density 0.424%

    No Known Activations