© 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. 20-GEMMASCOPE-RES-16K
    11. 8889
    Prev
    Next
    INDEX
    Explanations

    terms related to craniofacial anatomy and conditions

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

    Following "cran" or "Organ" (capitalized or not)

    np_acts-logits-general · gemini-2.0-flash

    cranium or head related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.88
    forRoot
    -0.86
    Tikang
    -0.81
    BibitemShut
    -0.77
     дописавши
    -0.76
    bewerken
    -0.74
     themſelves
    -0.72
    ductory
    -0.71
    onAttach
    -0.71
     Efq
    -0.71
    POSITIVE LOGITS
    n
    0.71
    ova
    0.70
    ama
    0.70
    ovo
    0.66
    ovsk
    0.65
    ov
    0.65
    y
    0.59
    ae
    0.57
    ovic
    0.56
    eh
    0.56
    Activations Density 0.200%

    No Known Activations