© 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. 11-GEMMASCOPE-RES-16K
    11. 10378
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people, locations, and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endblock
    -0.68
    Synonymes
    -0.66
    LookAnd
    -0.66
     Sandler
    -0.66
    RegressionTest
    -0.63
    PreferredItem
    -0.60
     CommonModule
    -0.59
     Houſe
    -0.58
     initData
    -0.56
     useRouter
    -0.56
    POSITIVE LOGITS
     Muhamma
    0.45
     PIO
    0.43
     Lucio
    0.41
    0.41
     Rasmus
    0.40
    Hawks
    0.40
    Flutter
    0.40
     SPO
    0.39
     phy
    0.39
    JMenuItem
    0.38
    Activations Density 2.202%

    No Known Activations