© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9404
    Prev
    Next
    INDEX
    Explanations

    references to revisions and updates in documents, particularly in relation to medical or scientific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.71
     AssemblyProduct
    -0.69
    ValueStyle
    -0.68
    ็จ
    -0.65
    Enllaces
    -0.64
    principalTable
    -0.61
     chi̍t
    -0.58
    tvguidetime
    -0.56
     Jesucristo
    -0.56
     ISNI
    -0.54
    POSITIVE LOGITS
    endphp
    0.72
    ों
    0.69
    blind
    0.68
     django
    0.67
    AndEndTag
    0.67
     Abstraction
    0.60
     blindness
    0.60
     Blind
    0.59
    Revision
    0.58
    django
    0.58
    Activations Density 0.056%

    No Known Activations