© 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. 7509
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rare."

    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
     fast
    -0.58
    a
    -0.58
    ty
    -0.55
    fle
    -0.55
    o
    -0.54
     and
    -0.53
     High
    -0.53
    -
    -0.52
     com
    -0.51
     
    -0.50
    POSITIVE LOGITS
     Majefty
    1.25
     Anſ
    1.16
     Jefus
    1.10
     purpoſe
    1.10
    ſelves
    1.09
     greateſt
    1.09
     itſelf
    1.07
     Efq
    1.04
     neceff
    1.04
     pleaſure
    1.03
    Activations Density 0.151%

    No Known Activations