© 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. 4-GEMMASCOPE-RES-16K
    11. 1948
    Prev
    Next
    INDEX
    Explanations

    references to specific measurements of diameter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.67
    InstanceState
    -0.62
     tris
    -0.59
     Missing
    -0.59
    Tris
    -0.59
     missing
    -0.58
     Tris
    -0.57
     nakalista
    -0.57
     nast
    -0.57
    endpush
    -0.57
    POSITIVE LOGITS
     diameter
    2.56
     Diameter
    2.26
    diameter
    2.21
     diameters
    2.15
    Diameter
    2.07
     radius
    1.92
    radius
    1.72
     diámetro
    1.61
     Durchmesser
    1.58
    直径
    1.58
    Activations Density 0.107%

    No Known Activations