© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13903
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting conditions and requirements related to actions or events

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

    conditions or circumstances

    np_acts-logits-general · gemini-2.0-flash

    ideas involve in processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ergies
    -0.56
    GIVEREF
    -0.53
    senz
    -0.48
    Cursors
    -0.46
     Derfor
    -0.45
     Managua
    -0.44
     Troop
    -0.44
    ToBounds
    -0.43
    avigation
    -0.43
     lemmas
    -0.42
    POSITIVE LOGITS
     שוליים
    1.04
    しかも
    1.00
     dabei
    0.80
     involves
    0.79
    Dabei
    0.78
     involve
    0.77
     melakukannya
    0.76
    новништво
    0.74
     involving
    0.71
     includes
    0.69
    Activations Density 0.791%

    No Known Activations