© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2011
    Prev
    Next
    INDEX
    Explanations

    instances of specific document structural elements or formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -1.77
     Shakspeare
    -1.31
    ↵
    -1.25
     myſelf
    -1.25
     Cæsar
    -1.19
     itſelf
    -1.14
     photolibrary
    -1.12
     ་་
    -1.09
     Mahomet
    -1.07
     Monfieur
    -1.07
    POSITIVE LOGITS
    ,
    1.23
     and
    0.95
     in
    0.92
     as
    0.86
     at
    0.83
     on
    0.82
     is
    0.81
     for
    0.80
     the
    0.79
     last
    0.77
    Activations Density 0.565%

    No Known Activations