Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3330
    Prev
    Next
    INDEX
    Explanations

    phrases related to networking and system performance metrics

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

    network transmission power

    np_acts-logits-general · gemini-2.0-flash

    network transmission scheduling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.66
    rungsseite
    -0.64
    TextWatcher
    -0.61
     sharpen
    -0.58
    AnchorStyles
    -0.57
     sharpened
    -0.55
    InSection
    -0.55
     sublimation
    -0.53
    oredCriteria
    -0.52
    Returned
    -0.52
    POSITIVE LOGITS
     routing
    0.71
     Routing
    0.63
     selfish
    0.62
     packet
    0.61
     distributed
    0.60
     fairness
    0.57
     nodes
    0.55
     node
    0.55
    \{\\
    0.54
    routing
    0.54
    Activations Density 0.606%

    No Known Activations