© 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. 23-GEMMASCOPE-RES-16K
    11. 12285
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and adjectives related to differences or advantages between items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
    flashdata
    -0.44
    xnn
    -0.37
    ]")]
    -0.36
     Consist
    -0.36
     gine
    -0.36
     correc
    -0.35
    NSIndexPath
    -0.33
     رائ
    -0.33
     consig
    -0.33
    CodeAnalysis
    -0.33
    POSITIVE LOGITS
    الدراسه
    0.66
     mijne
    0.63
     autorytatywna
    0.63
     meeste
    0.62
     zijne
    0.60
     früheren
    0.60
     diğer
    0.60
    aarrggbb
    0.60
     übrigen
    0.60
     صوتيه
    0.58
    Activations Density 0.511%

    No Known Activations