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. 183
    Prev
    Next
    INDEX
    Explanations

    declarations and annotations related to Java classes and methods

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

    the Java 'public' keyword in source code.

    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
    +#+
    -0.56
     <>",
    -0.51
    ngths
    -0.51
    Digitized
    -0.50
    sellor
    -0.50
    OrBuilder
    -0.49
    googleapis
    -0.49
    onton
    -0.48
     awning
    -0.48
    vitis
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    0.49
     nahilalakip
    0.48
     autorytatywna
    0.46
     <<<<<<<<<<<<<<
    0.46
     initComponents
    0.44
    endregion
    0.41
    __((
    0.38
    
    0.37
     AssemblyTitle
    0.37
     []:
    0.35
    Activations Density 0.012%

    No Known Activations