© 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. 11428
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and expressions of opinion

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Opening quotation marks followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    spoken dialogue openers

    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
    Negative Logits
     general
    -0.49
     la
    -0.43
    ・・・
    -0.43
     parse
    -0.43
     mesta
    -0.42
     extra
    -0.42
     series
    -0.41
     عنه
    -0.40
    ς
    -0.39
     معه
    -0.39
    POSITIVE LOGITS
    Parcelize
    0.86
    MockBean
    0.85
    jsxFileName
    0.79
    __*/
    0.79
     Theſe
    0.78
    JpaRepository
    0.75
    richTextPanel
    0.74
    клопе
    0.73
     myſelf
    0.72
     InputDecoration
    0.72
    Activations Density 0.125%

    No Known Activations