© 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. 34-GEMMASCOPE-RES-16K
    11. 10766
    Prev
    Next
    INDEX
    Explanations

    elements related to design and aesthetic features in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.40
    posedge
    -0.39
    MeasureSpec
    -0.38
    ViewChild
    -0.38
    AndEndTag
    -0.35
    :+:
    -0.34
    EndTag
    -0.33
    İstinadlar
    -0.33
    CloseOperation
    -0.32
    مصادر
    -0.31
    POSITIVE LOGITS
     enhance
    1.42
     adds
    1.41
     enhances
    1.36
     enhancing
    1.35
     adding
    1.28
    增添
    1.23
     Adds
    1.21
     enrich
    1.20
     Enhance
    1.17
    adds
    1.17
    Activations Density 0.415%

    No Known Activations