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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15422
    Prev
    Next
    INDEX
    Explanations

    mandatory requirements or obligations 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 @ 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
     Schie
    -0.48
    eaway
    -0.46
     Vallée
    -0.43
    figure
    -0.42
     Tiefen
    -0.42
    izier
    -0.39
     Sucher
    -0.39
     leyendo
    -0.39
    overview
    -0.39
     Feier
    -0.38
    POSITIVE LOGITS
     must
    1.61
     Must
    1.56
    Must
    1.53
    must
    1.45
    MUST
    1.26
     MUST
    1.26
     muſt
    0.92
     måste
    0.91
     harus
    0.87
     doit
    0.87
    Activations Density 0.106%

    No Known Activations