© 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. 16-GEMMASCOPE-RES-16K
    11. 15606
    Prev
    Next
    INDEX
    Explanations

    expressions of disappointment and confidence in personal qualities

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

    "usual" or "always" in context

    np_acts-logits-general · gemini-2.0-flash

    usual or always

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uros
    -0.61
    deka
    -0.57
    itorious
    -0.55
    imentel
    -0.51
    DataAnnotations
    -0.51
    rister
    -0.51
     ویکی‌پدیای
    -0.50
    OURCE
    -0.49
    πού
    -0.49
     čás
    -0.48
    POSITIVE LOGITS
     usual
    1.57
     always
    1.46
    usual
    1.43
    always
    1.41
    いつもの
    1.32
     Usual
    1.26
    Always
    1.25
     siempre
    1.24
     ALWAYS
    1.23
    今回も
    1.23
    Activations Density 0.232%

    No Known Activations