© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 16265
    Prev
    Next
    INDEX
    Explanations

    terms that describe relationships and comparisons of positional or quantitative attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zerű
    -0.47
    oogle
    -0.42
    miljø
    -0.36
     itinéraires
    -0.35
    μιουργ
    -0.35
    neté
    -0.35
     hindurch
    -0.34
    prüche
    -0.34
     eksemp
    -0.33
    Atsauces
    -0.33
    POSITIVE LOGITS
     relative
    2.34
    relative
    2.13
     Relative
    2.06
    Relative
    1.95
     RELATIVE
    1.94
     relatif
    1.63
     relativa
    1.54
    RELATIVE
    1.50
     relativo
    1.45
     относи
    1.41
    Activations Density 0.404%

    No Known Activations