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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11354
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions involving variable assignments and evaluations

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

    Letters followed by options in parentheses

    np_acts-logits-general · gemini-2.0-flash

    multiple choice answers

    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
    それと
    -0.59
     its
    -0.51
    참고
    -0.51
     otras
    -0.50
    AutoresizingMask
    -0.50
    localVar
    -0.50
    isième
    -0.50
    そちら
    -0.49
     Feel
    -0.49
    UNRELATED
    -0.48
    POSITIVE LOGITS
     autorytatywna
    0.72
    principalTable
    0.68
     disambiguazione
    0.65
     betweenstory
    0.64
    helves
    0.61
    verwijspagina
    0.61
    ชาย
    0.61
    eseorang
    0.60
     GeoNames
    0.59
    Personensuche
    0.58
    Activations Density 0.671%

    No Known Activations