© 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. 35-GEMMASCOPE-RES-16K
    11. 8074
    Prev
    Next
    INDEX
    Explanations

    mathematical or computational expressions and coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیای
    -0.46
    AndEndTag
    -0.38
    guigu
    -0.38
    SourceChecksum
    -0.37
     Jasmine
    -0.36
     Kokos
    -0.35
     mergeFrom
    -0.34
     lenker
    -0.34
    inson
    -0.34
     Serviço
    -0.34
    POSITIVE LOGITS
     four
    1.10
     Four
    1.08
     Fourth
    1.07
    4
    1.06
     fourth
    1.03
    Fourth
    1.00
     FOUR
    0.95
    Four
    0.94
     cuarto
    0.91
    four
    0.91
    Activations Density 1.435%

    No Known Activations