© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7708
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to filters and Banach spaces

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

    "Count", "ultra", or related mathematical concepts

    np_acts-logits-general · gemini-2.0-flash

    ultraproducts of banach spaces

    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
    TextAppearance
    -0.63
    UnsafeEnabled
    -0.59
     Moderato
    -0.59
     Wart
    -0.59
     Eup
    -0.59
     roulant
    -0.59
     Numerade
    -0.58
     Plutarch
    -0.58
     pollination
    -0.58
     vectorstock
    -0.57
    POSITIVE LOGITS
    countable
    0.65
     count
    0.62
    count
    0.58
     Count
    0.58
    Count
    0.57
     счет
    0.56
     measure
    0.55
     Cantor
    0.53
     счёт
    0.53
     COUN
    0.52
    Activations Density 1.230%

    No Known Activations