© 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. 5-GEMMASCOPE-RES-16K
    11. 15511
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thyself
    -0.64
     dónde
    -0.56
    jadi
    -0.56
     NgModule
    -0.54
    lyst
    -0.54
    quelles
    -0.53
     Longfellow
    -0.52
    rawDesc
    -0.51
     luogo
    -0.51
     artikkelen
    -0.51
    POSITIVE LOGITS
     With
    1.00
     WITH
    1.00
     with
    0.94
     Avec
    0.87
    With
    0.86
    IndentedString
    0.84
    with
    0.83
     avec
    0.81
    WITH
    0.81
    WithIdentifier
    0.75
    Activations Density 0.183%

    No Known Activations