© 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. 15-GEMMASCOPE-RES-16K
    11. 4555
    Prev
    Next
    INDEX
    Explanations

    terms related to notable individuals and their professions or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    رشف
    -0.84
    WithIOException
    -0.71
    hoeddwyd
    -0.68
    oa̍t
    -0.67
    twimg
    -0.67
    esez
    -0.65
    sigkeit
    -0.64
     '\\;'
    -0.63
    scalatest
    -0.62
     pageContext
    -0.61
    POSITIVE LOGITS
     who
    0.70
     whofe
    0.60
     whose
    0.59
     specialising
    0.57
     whom
    0.56
     origini
    0.56
     whoſe
    0.55
     extraordinaire
    0.55
     recientemente
    0.55
     specializing
    0.54
    Activations Density 0.186%

    No Known Activations