© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 4956
    Prev
    Next
    INDEX
    Explanations

    numerical values and currency symbols

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

    The number 8

    np_acts-logits-general · gemini-2.0-flash

    sequence of numbers ending in 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.52
    UrlResolution
    -0.52
    amal
    -0.50
     Simeon
    -0.50
    Izvori
    -0.50
    /***/
    -0.50
    Damon
    -0.48
    onite
    -0.47
    Fordítás
    -0.47
     Sandler
    -0.47
    POSITIVE LOGITS
    8
    1.62
     Eighth
    1.26
     eighth
    1.23
     eight
    1.21
     Eight
    1.21
     EIGHT
    1.14
     Eighty
    1.11
     eighty
    1.10
    八
    1.09
    Eight
    1.08
    Activations Density 0.686%

    No Known Activations