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. 16-GEMMASCOPE-RES-16K
    6. 5269
    Prev
    Next
    INDEX
    Explanations

    references to different versions or editions of materials

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

    "version" or "edition"

    np_acts-logits-general · gemini-2.0-flash

    versions and editions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.72
    makeConstraints
    -0.67
    titleMargin
    -0.57
     crin
    -0.57
     اكتوبر
    -0.57
    ConstraintMaker
    -0.56
    CloseOperation
    -0.56
     Италијани
    -0.56
    ')):
    -0.55
    HomeAsUp
    -0.55
    POSITIVE LOGITS
     version
    0.75
     versions
    0.73
     VERSION
    0.68
     hereof
    0.67
     of
    0.67
     rosca
    0.66
     edition
    0.64
     版本
    0.64
     EconPapers
    0.63
     thereof
    0.63
    Activations Density 0.512%

    No Known Activations