© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8322
    Prev
    Next
    INDEX
    Explanations

    references to insignificance or a lack of quantity and importance

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

    Follows "little" or indicates a small amount

    np_acts-logits-general · gemini-2.0-flash

    little followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -1.03
    Климат
    -0.59
    ConstraintMaker
    -0.54
     AssemblyTitle
    -0.52
    onomía
    -0.52
     }{@
    -0.51
     AssemblyProduct
    -0.51
     للاسماء
    -0.50
     ivelany
    -0.47
    dymyr
    -0.47
    POSITIVE LOGITS
    styleable
    0.71
     chance
    0.70
     semblance
    0.69
     resemblance
    0.68
     discernible
    0.66
     clue
    0.64
    riction
    0.60
     discer
    0.59
    chance
    0.59
     resembling
    0.58
    Activations Density 0.283%

    No Known Activations