© 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. 6540
    Prev
    Next
    INDEX
    Explanations

    references to external sources or citations in the text

    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
     Signalez
    -0.78
    ViewFeatures
    -0.77
     Ume
    -0.67
    .*")]
    -0.66
     MenuView
    -0.66
     jsPsych
    -0.64
    Unmanaged
    -0.63
    FieldNumber
    -0.63
    ñales
    -0.63
    ividual
    -0.62
    POSITIVE LOGITS
    see
    2.19
    See
    2.16
     See
    2.13
     see
    1.68
    SEE
    1.61
     SEE
    1.53
    siehe
    1.37
     Siehe
    1.28
     siehe
    1.27
    参见
    1.21
    Activations Density 0.105%

    No Known Activations