© 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. 6383
    Prev
    Next
    INDEX
    Explanations

    instances of character encoding specifications, particularly UTF-8

    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
    niſſe
    -0.70
    RenderAtEndOf
    -0.69
    ロウィン
    -0.63
     nahilalakip
    -0.63
    нгред
    -0.60
    iſchen
    -0.59
     JpaRepository
    -0.59
     erſt
    -0.57
    ſammen
    -0.57
     ſelbſt
    -0.56
    POSITIVE LOGITS
     charset
    1.01
    StandardCharsets
    0.91
    charset
    0.87
    Charset
    0.79
    Encoding
    0.75
     encoding
    0.64
     Encoding
    0.63
    Charsets
    0.61
    encoding
    0.60
    ENCODING
    0.56
    Activations Density 0.408%

    No Known Activations