© 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. 33-GEMMASCOPE-RES-16K
    11. 14405
    Prev
    Next
    INDEX
    Explanations

    references to advice or guidance

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

    No Comments

    Negative Logits
     étrangères
    -0.39
     ब्रेकडाउन
    -0.38
    versiti
    -0.37
    󠁢
    -0.35
    AnimationsModule
    -0.34
    getFullYear
    -0.34
    metery
    -0.33
     raven
    -0.33
    darah
    -0.33
    TEntity
    -0.31
    POSITIVE LOGITS
    MLLoader
    0.66
     leaflets
    0.52
    uyện
    0.51
    zzleHttp
    0.51
     disambiguazione
    0.50
     Counsel
    0.50
    ANDUM
    0.50
     Advice
    0.49
     given
    0.49
    riwal
    0.49
    Activations Density 0.183%

    No Known Activations