© 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. 3-GEMMASCOPE-RES-16K
    6. 8013
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Se" and its variants related to sequences or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.85
    ########.
    -0.81
     autorytatywna
    -0.80
     برانيه
    -0.79
     Frat
    -0.76
     Arquivado
    -0.67
     sobra
    -0.63
     burch
    -0.62
     Tinto
    -0.62
     Worthington
    -0.61
    POSITIVE LOGITS
     Se
    2.92
    Se
    2.85
     se
    2.53
     SE
    2.38
    SE
    2.19
    se
    2.14
     Sé
    1.63
    Sé
    1.51
     Seb
    1.49
     Seidel
    1.46
    Activations Density 0.123%

    No Known Activations