© 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. 7-GEMMASCOPE-RES-16K
    11. 15466
    Prev
    Next
    INDEX
    Explanations

    references to duchies and titles associated with nobility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.44
    AndEndTag
    -0.42
     chofe
    -0.41
    twimg
    -0.40
    脚注の使い方
    -0.39
    ViewFeatures
    -0.39
     fevere
    -0.38
    Становништво
    -0.38
    mbols
    -0.37
     enfans
    -0.37
    POSITIVE LOGITS
     du
    2.45
     Du
    2.44
    Du
    2.39
     DU
    2.20
    du
    2.08
    DU
    1.87
    デュ
    1.53
     Duval
    1.46
     Dup
    1.46
     ду
    1.45
    Activations Density 0.159%

    No Known Activations