© 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. 11-GEMMASCOPE-RES-16K
    11. 3945
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate continuation or reference to "the rest of" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    openConnection
    -0.76
     Drapeau
    -0.72
    bunal
    -0.62
    isbol
    -0.61
    oubtedly
    -0.60
     peau
    -0.55
    quine
    -0.55
     InputDecoration
    -0.54
    lück
    -0.53
     Councilman
    -0.53
    POSITIVE LOGITS
     resten
    1.14
     rest
    1.00
     pozosta
    0.89
     remainder
    0.88
     Remaining
    0.80
     remaining
    0.79
     übrigen
    0.79
    Remaining
    0.77
    +#+#
    0.77
     остальные
    0.76
    Activations Density 0.073%

    No Known Activations