© 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. 1-GEMMASCOPE-RES-16K
    11. 11118
    Prev
    Next
    INDEX
    Explanations

    terms indicating rarity or unusualness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     furnish
    -0.58
    mopolitan
    -0.53
     DNA
    -0.53
     volont
    -0.52
     posY
    -0.51
    slick
    -0.51
    ADN
    -0.51
    kwds
    -0.49
    DNA
    -0.49
     duque
    -0.48
    POSITIVE LOGITS
     rare
    1.70
     Rare
    1.49
    Rare
    1.43
    rare
    1.27
     RARE
    1.22
     rarest
    1.19
     rarity
    1.18
     rarer
    1.16
     rares
    1.11
     triple
    1.06
    Activations Density 0.053%

    No Known Activations