© 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. 12995
    Prev
    Next
    INDEX
    Explanations

    terms related to machine learning and computing concepts

    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
    ValueStyle
    -0.82
     Bex
    -0.77
     Eko
    -0.73
    IBar
    -0.72
    DotNetBar
    -0.70
     Kaka
    -0.70
     Easton
    -0.69
     isk
    -0.68
     Morm
    -0.68
     Alfa
    -0.66
    POSITIVE LOGITS
    uuuu
    0.99
    uu
    0.95
    uuu
    0.91
    UU
    0.83
     Underwood
    0.83
    ungeon
    0.81
    UUUU
    0.81
    uuuuu
    0.80
    ubus
    0.78
     UU
    0.77
    Activations Density 8.969%

    No Known Activations