© 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. 0-GEMMASCOPE-RES-16K
    11. 7574
    Prev
    Next
    INDEX
    Explanations

    assertions of certainty or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CGRectMake
    -0.73
     TimeUnit
    -0.67
     ་་
    -0.64
     CGRectMake
    -0.63
     Houſe
    -0.62
     auffi
    -0.62
     fists
    -0.61
     tromper
    -0.61
     Charlemagne
    -0.61
    uarts
    -0.60
    POSITIVE LOGITS
    évaluateur
    0.68
     dé
    0.68
    Meditation
    0.59
     meditation
    0.58
     partition
    0.58
     Medicare
    0.55
    خواندن
    0.55
     gr
    0.55
     transmission
    0.52
    writeFieldEnd
    0.52
    Activations Density 0.058%

    No Known Activations