© 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. 16-GEMMASCOPE-RES-16K
    11. 10367
    Prev
    Next
    INDEX
    Explanations

    mentions of public figures and their interactions, often in a political or legal context

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

    Tokens preceding names or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    names and titles

    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
    Negative Logits
    出版年
    -0.85
     الرياضيه
    -0.76
    webElementXpaths
    -0.64
    cipline
    -0.57
    itarianism
    -0.57
    estyles
    -0.55
     CreateTagHelper
    -0.54
    ]")]
    -0.52
    agonal
    -0.52
    ophobia
    -0.51
    POSITIVE LOGITS
     via
    0.60
     perquè
    0.59
     during
    0.55
     when
    0.55
    ControllerAdvice
    0.53
    StructEnd
    0.53
     once
    0.49
     affinch
    0.49
     supaya
    0.47
    הערות
    0.47
    Activations Density 0.586%

    No Known Activations