© 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. 23-GEMMASCOPE-RES-16K
    11. 13914
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that indicate relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.90
    Vidite
    -0.77
    ticularly
    -0.76
    fjspx
    -0.76
    AndEndTag
    -0.73
    contentLoaded
    -0.71
    ValueStyle
    -0.70
     henceforth
    -0.69
    writeFieldEnd
    -0.67
    HtmlAttribute
    -0.67
    POSITIVE LOGITS
     lots
    1.50
     plenty
    1.45
     ample
    1.20
    lots
    1.17
     LOTS
    1.15
     Lots
    1.12
     great
    1.11
     tons
    1.11
    Lots
    1.10
     excellent
    1.09
    Activations Density 0.331%

    No Known Activations