© 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. 20-GEMMASCOPE-RES-16K
    11. 3376
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual or entity associated with a business or organization

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

    "Impact Factory" followed by "utah" or email addresses

    np_acts-logits-general · gemini-2.0-flash

    Impact Factory Utah

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     a
    -0.89
     
    -0.86
     I
    -0.86
    ,
    -0.83
     in
    -0.78
     B
    -0.78
     P
    -0.78
     (
    -0.77
     S
    -0.76
     D
    -0.76
    POSITIVE LOGITS
     Anſ
    1.33
     Shakspeare
    1.33
     Theſe
    1.32
     Reſ
    1.32
     Diſ
    1.31
     Jefus
    1.26
     Efq
    1.23
     ་་
    1.21
     ſeveral
    1.20
     Houſe
    1.19
    Activations Density 0.212%

    No Known Activations