© 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. 34-GEMMASCOPE-RES-16K
    11. 16014
    Prev
    Next
    INDEX
    Explanations

    French determiners and articles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    föra
    -0.63
    ſelves
    -0.62
    farande
    -0.60
    makeText
    -0.60
    TypedDataSet
    -0.60
    ällor
    -0.59
    område
    -0.59
    forhold
    -0.59
    RenderAtEndOf
    -0.59
    ſelf
    -0.58
    POSITIVE LOGITS
    pă
    0.47
     betrekking
    0.46
    toare
    0.44
     היתה
    0.43
     bune
    0.41
     bună
    0.40
     tavo
    0.40
    toarele
    0.40
     lumea
    0.40
    țele
    0.39
    Activations Density 0.073%

    No Known Activations