Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10311
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formatting elements across the document

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

    HTML list or table formatting tags

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and lists

    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
     autorytatywna
    -1.09
     "..\..\..\
    -0.81
     "..\..\
    -0.81
     يتيمه
    -0.78
    MLLoader
    -0.78
    Personendaten
    -0.76
    ConstraintMaker
    -0.74
    GEBURTSDATUM
    -0.73
     betweenstory
    -0.72
     ویکی‌پدیا
    -0.71
    POSITIVE LOGITS
    br
    0.74
    table
    0.63
    hr
    0.59
     br
    0.57
    ol
    0.56
     table
    0.54
    BR
    0.53
    p
    0.52
    orderList
    0.52
    P
    0.51
    Activations Density 0.441%

    No Known Activations