© 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. 22-GEMMASCOPE-RES-16K
    11. 3683
    Prev
    Next
    INDEX
    Explanations

    references to individuals or surnames, particularly those starting with "Ber"

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

    or names starting with "Ber"

    np_acts-logits-general · gemini-2.0-flash

    words beginning with "Ber"

    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
     AssemblyCulture
    -0.77
    ValueStyle
    -0.69
     Devonian
    -0.61
    masalah
    -0.57
     Roskov
    -0.54
    Abit
    -0.53
    Cyfarwyddwr
    -0.53
    Cyfeiriadau
    -0.52
    addSubview
    -0.52
    uegos
    -0.52
    POSITIVE LOGITS
    Ber
    0.74
     Ber
    0.67
     Berk
    0.62
     CreateTagHelper
    0.58
     BER
    0.57
     Beres
    0.56
    PerformLayout
    0.55
     beret
    0.55
     beru
    0.55
     Bertie
    0.54
    Activations Density 0.080%

    No Known Activations