© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14722
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LUMP
    -0.62
    end
    -0.59
    پیوند
    -0.59
    mathrm
    -0.56
     Speicher
    -0.55
    XOXO
    -0.51
    abestanden
    -0.51
    begin
    -0.51
     menta
    -0.50
    textnormal
    -0.49
    POSITIVE LOGITS
    SBATCH
    0.96
     consecration
    0.89
     Khrushchev
    0.87
     Arjuna
    0.86
     "..\..\..\
    0.84
    orghini
    0.82
     bellows
    0.81
     poppies
    0.81
    :✨
    0.79
     colloidal
    0.78
    Activations Density 0.893%

    No Known Activations