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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8304
    Prev
    Next
    INDEX
    Explanations

    JSON-like structures containing key-value pairs

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

    The token "value" followed by a colon

    np_acts-logits-general · gemini-2.0-flash

    value assignment or attribute

    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
    AnchorStyles
    -0.86
     Superhosts
    -0.79
     ISNI
    -0.75
    coroutines
    -0.73
     فريبيس
    -0.73
    gonic
    -0.71
    awaiter
    -0.70
     المعيارى
    -0.68
     Lorentz
    -0.67
    CompilerServices
    -0.66
    POSITIVE LOGITS
     values
    1.26
     Values
    1.13
    VALUE
    1.09
     value
    1.06
     Value
    1.06
     VALUE
    1.06
    values
    1.05
    Wert
    1.02
    Values
    0.99
    Value
    0.98
    Activations Density 0.119%

    No Known Activations