© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5150
    Prev
    Next
    INDEX
    Explanations

    references to institutions and academic terminology related to research and law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Catawiki
    -0.63
    profen
    -0.59
    αρα
    -0.56
    IZONTAL
    -0.56
    ginous
    -0.54
    WindowConstants
    -0.53
    UCKY
    -0.52
    uscular
    -0.52
    مت
    -0.51
    ANEOUS
    -0.51
    POSITIVE LOGITS
     of
    1.50
    Portail
    1.11
    of
    0.80
     của
    0.79
    ंदीखरीदारी
    0.77
    GraphicsUnit
    0.77
     transférez
    0.76
     GlobalKey
    0.75
     beginnetje
    0.75
     MessageBoxIcon
    0.74
    Activations Density 0.998%

    No Known Activations