© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9182
    Prev
    Next
    INDEX
    Explanations

    the presence of a document's structural elements or metadata indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.96
     reaſon
    -0.89
     reafon
    -0.84
     feroit
    -0.84
     Majefty
    -0.83
     deſt
    -0.80
     Jefus
    -0.79
     raiſ
    -0.79
     purpoſe
    -0.77
     neceſſ
    -0.77
    POSITIVE LOGITS
    󠁿
    0.71
    i
    0.68
    s
    0.68
    o
    0.63
    a
    0.60
    )
    0.58
     متعلقه
    0.56
    л
    0.55
    (
    0.53
    es
    0.52
    Activations Density 0.031%

    No Known Activations