© 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. 14369
    Prev
    Next
    INDEX
    Explanations

    phrases related to logic and conditional statements

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

    "otherwise" and related conditional words

    np_acts-logits-general · gemini-2.0-flash

    otherwise

    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
    cheinend
    -0.56
    memoized
    -0.55
     Exacts
    -0.49
    Története
    -0.46
    encodeWith
    -0.46
    Дереккөздер
    -0.45
    necedor
    -0.44
    styleType
    -0.44
    ódó
    -0.43
    してみる
    -0.43
    POSITIVE LOGITS
     otherwise
    4.22
     Otherwise
    3.90
    Otherwise
    3.89
    otherwise
    3.78
     OTHERWISE
    3.45
     altrimenti
    3.14
     ellers
    2.69
     else
    2.68
    否则
    2.65
     иначе
    2.64
    Activations Density 0.420%

    No Known Activations