© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3497
    Prev
    Next
    INDEX
    Explanations

    the word "where" indicating a focus on location or context within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    when introducing clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OCS
    -0.57
     AIP
    -0.57
     Apoll
    -0.57
    them
    -0.56
    zeß
    -0.56
     dlaczego
    -0.54
     őket
    -0.54
     falando
    -0.53
     PFS
    -0.52
     ddelweddau
    -0.52
    POSITIVE LOGITS
     they
    1.16
     there
    0.95
     we
    0.92
     it
    0.85
     Où
    0.81
     you
    0.81
    upon
    0.79
    unto
    0.78
    ever
    0.76
     he
    0.73
    Activations Density 0.082%

    No Known Activations