© 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. 2824
    Prev
    Next
    INDEX
    Explanations

    negations and their implications in the text

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

    Follows "not" or "t"

    np_acts-logits-general · gemini-2.0-flash

    not going to

    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
    rather
    -0.80
     ſever
    -0.77
     Efq
    -0.77
     $_"
    -0.75
    NUMX
    -0.72
     itſelf
    -0.70
    ^(@)
    -0.69
     piuttosto
    -0.68
     rather
    -0.68
     myſelf
    -0.67
    POSITIVE LOGITS
    LookAnd
    0.65
     nor
    0.62
     any
    0.57
    richTextPanel
    0.54
    TypedDataSet
    0.53
    nor
    0.47
    !
    0.45
    !");
    0.45
     "
    0.45
     want
    0.43
    Activations Density 0.375%

    No Known Activations