© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1365
    Prev
    Next
    INDEX
    Explanations

    references to specific people, places, or organizations

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

    Followed by relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.74
    出版年
    -0.74
    WithIOException
    -0.68
    олові
    -0.65
     kasarigan
    -0.64
    ronpa
    -0.64
    +#+#
    -0.62
    ِّف
    -0.62
    iastes
    -0.61
    ImageContext
    -0.57
    POSITIVE LOGITS
     which
    2.17
    which
    1.86
     who
    1.47
     WHICH
    1.42
     whose
    1.29
    ซึ่ง
    1.24
    Which
    1.24
     whom
    1.23
     Which
    1.22
    whose
    1.20
    Activations Density 0.753%

    No Known Activations