© 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 EvalsExportsinterp-engineNEWAPI 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. 12271
    Prev
    Next
    INDEX
    Explanations

    statistical references and citations in research documents

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

    Numbers enclosed in square brackets

    np_acts-logits-general · gemini-2.0-flash

    academic citations with numbers

    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
     ?>/
    -0.62
    뀐
    -0.48
    rootScope
    -0.47
    Халык
    -0.45
     today
    -0.45
    asInstanceOf
    -0.44
    حوالہ
    -0.44
     conto
    -0.43
    bParam
    -0.43
    ofition
    -0.42
    POSITIVE LOGITS
     linkovi
    0.78
    InjectAttribute
    0.72
    Portale
    0.70
     postIndex
    0.69
    ServletException
    0.68
    DeleteBehavior
    0.67
    RunWith
    0.67
    XmlAccessorType
    0.66
    Personendaten
    0.63
    ValueStyle
    0.62
    Activations Density 0.227%

    No Known Activations