© 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. 22-GEMMASCOPE-RES-16K
    11. 3191
    Prev
    Next
    INDEX
    Explanations

    phrases indicating involvement or contribution to a larger whole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.44
     méda
    -0.44
     vrou
    -0.40
    intervento
    -0.38
     inappropriés
    -0.38
     poszczegól
    -0.37
     vraag
    -0.36
     producenta
    -0.36
     producido
    -0.35
    ificantly
    -0.35
    POSITIVE LOGITS
     part
    0.74
     частью
    0.68
    enumi
    0.67
     Bestandteil
    0.61
     Teil
    0.61
    的一部分
    0.59
     addTo
    0.58
    part
    0.58
     часть
    0.57
     ضمن
    0.56
    Activations Density 0.328%

    No Known Activations