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. 19-GEMMASCOPE-RES-16K
    6. 2858
    Prev
    Next
    INDEX
    Explanations

    URLs and references to web resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.55
    ↵
    -0.50
    <eos>
    -0.50
     E
    -0.49
    ↵↵
    -0.48
     [
    -0.48
     "
    -0.47
     May
    -0.46
     an
    -0.46
     B
    -0.46
    POSITIVE LOGITS
    Datuak
    0.99
     незавершена
    0.96
     BorderRadius
    0.90
     فريبيس
    0.90
     المعيارى
    0.88
     doubtnut
    0.88
     themſelves
    0.87
     ſmall
    0.86
     ویکی‌پدیای
    0.85
     myſelf
    0.85
    Activations Density 0.178%

    No Known Activations