© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13217
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or clarification

    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
     مشين
    -0.54
     vVar
    -0.47
    わけです
    -0.47
    けどね
    -0.43
    PostExecute
    -0.42
    みよう
    -0.41
    やってきた
    -0.41
    みました
    -0.41
    ことはありません
    -0.41
    かというと
    -0.40
    POSITIVE LOGITS
     please
    3.20
     Please
    2.67
    please
    2.66
    Please
    2.55
     PLEASE
    2.44
     plz
    2.11
    PLEASE
    2.11
     pls
    2.08
     bitte
    2.02
     Bitte
    1.99
    Activations Density 0.471%

    No Known Activations