© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15074
    Prev
    Next
    INDEX
    Explanations

    important dates and historical events, particularly related to significant wars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']]
    -0.62
    meldung
    -0.60
     NACIONAL
    -0.58
     blij
    -0.58
     Emin
    -0.57
    erate
    -0.57
    Emin
    -0.56
    setdefault
    -0.55
     pamięci
    -0.55
    Geplaatst
    -0.55
    POSITIVE LOGITS
    PreferredItem
    0.84
    actionMode
    0.73
    roek
    0.67
    andExpect
    0.66
     betweenstory
    0.65
    scriptcase
    0.63
     aDecoder
    0.63
    fcntl
    0.63
    messageInfo
    0.63
    󠁣
    0.62
    Activations Density 0.143%

    No Known Activations