© 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. 3-GEMMASCOPE-RES-16K
    11. 3072
    Prev
    Next
    INDEX
    Explanations

    words related to various types of clothing and accessories, particularly focusing on "bow" as a key term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.52
    UnusedPrivate
    -0.49
    حوالہ
    -0.47
    PRNewswire
    -0.47
    \{\\
    -0.47
    IBinder
    -0.46
    Kjelder
    -0.46
     Signalez
    -0.45
     Absol
    -0.43
    Absol
    -0.42
    POSITIVE LOGITS
     Bow
    0.75
     bow
    0.75
     sweat
    0.72
     BOW
    0.69
    Bow
    0.69
    bow
    0.68
    sweat
    0.64
    BOW
    0.63
     Sweat
    0.62
     sweating
    0.61
    Activations Density 1.388%

    No Known Activations