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

    Neuronpedia

    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. 8508
    Prev
    Next
    INDEX
    Explanations

    names and references related to individuals and entities, particularly 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 @ 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
     Sech
    -0.50
     Bren
    -0.50
     Buster
    -0.49
    nictwa
    -0.48
     Baj
    -0.47
     Lons
    -0.46
     Sigism
    -0.45
    abstractmethod
    -0.45
    MediaStore
    -0.45
    IntegrationTest
    -0.44
    POSITIVE LOGITS
    躇
    0.59
     Bewußt
    0.57
     للمعارف
    0.56
    ніципалі
    0.53
    Kanpo
    0.51
     macetas
    0.50
    agré
    0.50
    Mafia
    0.49
    ValueStyle
    0.48
     '\\;'
    0.48
    Activations Density 1.844%

    No Known Activations