© 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. 20-GEMMASCOPE-RES-16K
    11. 8494
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and symbols related to mathematics or science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical/mathematical notation and scientific terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     رش
    -0.40
     pocket
    -0.37
    sprüng
    -0.37
     initComponents
    -0.37
    ]=>
    -0.36
    CloseOperation
    -0.35
    wani
    -0.33
    против
    -0.33
    regu
    -0.33
     sahi
    -0.33
    POSITIVE LOGITS
    лтемелер
    0.57
     linkovi
    0.53
    帖最后由
    0.50
    DispatchToProps
    0.46
     Administrativna
    0.45
     muligt
    0.44
     iParam
    0.44
    principalColumn
    0.44
    İstinadlar
    0.43
    
    0.42
    Activations Density 0.334%

    No Known Activations