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. 22-GEMMASCOPE-RES-16K
    6. 6005
    Prev
    Next
    INDEX
    Explanations

    references to government and official documents related to aviation

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

    Code or formula snippets

    np_acts-logits-general · gemini-2.0-flash

    India's Oscar entries or Krishna Reddy

    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
     surla
    -0.58
     municipality
    -0.56
     Timoteo
    -0.54
    ">//
    -0.52
     conosco
    -0.50
     statewide
    -0.49
    WindowConstants
    -0.48
    District
    -0.48
    dbo
    -0.48
    Provincial
    -0.48
    POSITIVE LOGITS
    참고
    0.68
     Union
    0.64
     Indian
    0.62
    windowFixed
    0.59
     Modi
    0.57
    سطس
    0.56
     India
    0.56
    makeConstraints
    0.56
    KeySpec
    0.56
    таратура
    0.54
    Activations Density 0.083%

    No Known Activations