© 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. 20-GEMMASCOPE-RES-16K
    11. 3543
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating a lack of something

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

    Follows "any"

    np_acts-logits-general · gemini-2.0-flash

    any

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kadang
    -0.67
     alguns
    -0.66
     algunas
    -0.65
     suivants
    -0.62
     suficientemente
    -0.62
     algumas
    -0.60
     Enough
    -0.60
     algunos
    -0.59
    transQ
    -0.57
     alcuni
    -0.56
    POSITIVE LOGITS
     sort
    1.31
     kind
    1.27
    sort
    0.90
     semblance
    0.89
     particular
    0.85
     further
    0.84
     indication
    0.83
    kind
    0.82
     SORT
    0.74
     Sort
    0.74
    Activations Density 0.326%

    No Known Activations