© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2711
    Prev
    Next
    INDEX
    Explanations

    references to bars and their varying attributes or measurements

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

    HTML and programming-related elements like "bar", code snippets, and UI components.

    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
     Toussaint
    -0.45
    :''
    -0.40
    ụng
    -0.37
    ^)
    -0.35
     Therese
    -0.35
    willi
    -0.35
    complete
    -0.35
    you
    -0.34
    :"",
    -0.34
    offensive
    -0.34
    POSITIVE LOGITS
     Bar
    1.13
     bar
    1.09
    Bar
    1.07
    Bars
    1.04
    bars
    1.02
     Bars
    1.02
     bars
    0.98
     BAR
    0.97
    BAR
    0.96
    bar
    0.96
    Activations Density 0.103%

    No Known Activations