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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 90117
    Prev
    Next
    INDEX
    Explanations

    specific numerical data, particularly relating to research references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    TagMode
    -0.61
     realities
    -0.56
     linkovi
    -0.54
    Хьажоргаш
    -0.50
     ErrIntOverflow
    -0.50
    -------------</
    -0.49
    iric
    -0.49
    savevideo
    -0.49
    WebElementEntity
    -0.49
    ouſly
    -0.48
    POSITIVE LOGITS
     conmigo
    0.52
    TestingModule
    0.45
    endcsname
    0.41
     HasFactory
    0.38
     contigo
    0.35
    openConnection
    0.34
     kaynağından
    0.34
    IsPostBack
    0.34
     comigo
    0.33
    Földrajzportál
    0.31
    Activations Density 0.016%

    No Known Activations