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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12733
    Prev
    Next
    INDEX
    Explanations

    references to educational resources and publications related to learning materials

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

    books, guides, and collections

    np_acts-logits-general · gemini-2.0-flash

    reference books

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.74
    onViewCreated
    -0.70
    parsedMessage
    -0.66
     Pingback
    -0.65
    dflare
    -0.65
    Geplaatst
    -0.64
    writerow
    -0.61
    thâu
    -0.61
     onResponse
    -0.60
     ivelany
    -0.60
    POSITIVE LOGITS
     handbook
    1.18
     guide
    1.12
     book
    1.05
     manual
    1.01
     Handbook
    0.99
     Guide
    0.96
     volume
    0.96
     reference
    0.93
    Handbook
    0.91
     encyclopedia
    0.89
    Activations Density 0.327%

    No Known Activations