© 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. 7379
    Prev
    Next
    INDEX
    Explanations

    closing and semi-colon punctuation marks used in programming 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
     ModelExpression
    -0.79
     EconPapers
    -0.69
    TagMode
    -0.61
     Photocase
    -0.54
     فريبيس
    -0.54
     resourceCulture
    -0.54
     Monfieur
    -0.54
     Chwiliwch
    -0.53
    DECREF
    -0.53
     ویکی‌پدی
    -0.53
    POSITIVE LOGITS
     pertanto
    0.46
     Jadi
    0.41
     serait
    0.40
     więc
    0.40
     therefore
    0.38
    Referencies
    0.38
     jadi
    0.38
     is
    0.38
     perciò
    0.36
    seamnă
    0.36
    Activations Density 0.168%

    No Known Activations