© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 6850
    Prev
    Next
    INDEX
    Explanations

    code structures and syntactical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -1.04
     pleaſure
    -0.99
     Theſe
    -0.97
     myſelf
    -0.96
     uſe
    -0.94
     houſe
    -0.93
     iſt
    -0.93
     ſtate
    -0.92
     leaſt
    -0.92
     ſeveral
    -0.92
    POSITIVE LOGITS
     and
    0.99
    ,
    0.86
     or
    0.77
     in
    0.75
     which
    0.75
     as
    0.69
     at
    0.66
     for
    0.65
     also
    0.63
     on
    0.62
    Activations Density 0.725%

    No Known Activations