© 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. 3-GEMMASCOPE-RES-16K
    11. 7852
    Prev
    Next
    INDEX
    Explanations

    phrases associated with instructions or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sk
    -0.70
     ste
    -0.65
     bet
    -0.63
     p
    -0.63
     inv
    -0.63
    -
    -0.62
     sti
    -0.61
     re
    -0.61
    見
    -0.60
     ri
    -0.60
    POSITIVE LOGITS
     myſelf
    1.53
     himſelf
    1.50
     itſelf
    1.48
     auffi
    1.44
     ſeveral
    1.42
    ſelf
    1.42
     themſelves
    1.41
     ainfi
    1.39
     againſt
    1.38
     ſhe
    1.37
    Activations Density 0.164%

    No Known Activations