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. 311
    Prev
    Next
    INDEX
    Explanations

    Java access modifiers and visibility keywords in code

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

    Java programming language syntax and keywords like 'public', 'static', 'class', etc.

    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
    исленность
    -0.51
     daraus
    -0.39
     Dadurch
    -0.37
     rechange
    -0.36
     whereas
    -0.36
    paramref
    -0.36
     sebaliknya
    -0.35
     tandis
    -0.35
     toit
    -0.35
     instead
    -0.34
    POSITIVE LOGITS
     initComponents
    0.71
     الحره
    0.68
     propOrder
    0.64
    Personendaten
    0.58
    IContainer
    0.56
     StatefulWidget
    0.54
    MessageOf
    0.54
    private
    0.54
    Personensuche
    0.53
    FXML
    0.52
    Activations Density 0.035%

    No Known Activations