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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1835
    Prev
    Next
    INDEX
    Explanations

    elements and attributes in coding and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.98
    tagext
    -0.78
    dafx
    -0.75
     चीज़ों
    -0.75
    #
    -0.75
     EconPapers
    -0.74
    extAlignment
    -0.73
    IntoConstraints
    -0.73
    原始内容存档于
    -0.71
    estacks
    -0.69
    POSITIVE LOGITS
    <eos>
    0.57
    ↵↵
    0.53
     becauſe
    0.45
    ↵
    0.45
    '])){
    
    0.44
    ));
    0.44
     olives
    0.43
    '])){
    0.42
    Fonti
    0.42
     vklju
    0.41
    Activations Density 0.096%

    No Known Activations