Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 161
    Prev
    Next
    INDEX
    Explanations

    technical language related to image processing and transformations

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

    programming code or mathematical operations, particularly related to image processing and grid transformations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     utafitiHapana
    -0.34
     sappiamo
    -0.32
    hoeddwyd
    -0.29
     vzduchu
    -0.29
     arşivlendi
    -0.29
    extAlignment
    -0.29
    webElementGuid
    -0.28
    AddTagHelper
    -0.28
     allemaal
    -0.28
    헌
    -0.27
    POSITIVE LOGITS
    argout
    0.70
    matlab
    0.68
    chartInstance
    0.68
     eventdata
    0.65
    ulink
    0.63
     matlab
    0.60
     MATLAB
    0.60
    ⓧ
    0.57
    ViewImports
    0.57
     Matlab
    0.57
    Activations Density 0.231%

    No Known Activations