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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3589
    Prev
    Next
    INDEX
    Explanations

    HTML button elements and their attributes in the text

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

    HTML button tags and related terms

    np_acts-logits-general · gemini-2.0-flash

    UI button code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    <i>
    -0.41
     perdere
    -0.41
     bakım
    -0.40
    scape
    -0.39
    Wide
    -0.39
    OrWhiteSpace
    -0.38
     Merri
    -0.37
     Wide
    -0.37
    '));
    
    -0.37
     Eindruck
    -0.37
    POSITIVE LOGITS
     Button
    1.41
     button
    1.37
    button
    1.35
    Button
    1.33
     BUTTON
    1.24
     Buttons
    1.21
     UIButton
    1.21
     buttons
    1.14
    BUTTON
    1.13
     JButton
    1.13
    Activations Density 0.121%

    No Known Activations