© 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. 3-GEMMASCOPE-RES-16K
    11. 6703
    Prev
    Next
    INDEX
    Explanations

    references to various programs, particularly in an academic or organizational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    createCell
    -0.78
     Cuthbert
    -0.72
     validés
    -0.71
    etches
    -0.71
    AlterField
    -0.69
     Gaunt
    -0.68
    UnusedPrivate
    -0.68
     abstrait
    -0.67
     médicaux
    -0.66
    EDEFAULT
    -0.66
    POSITIVE LOGITS
     program
    3.20
     programs
    3.02
     Program
    2.88
     Programs
    2.72
    Program
    2.69
    programs
    2.65
    program
    2.64
    Programs
    2.64
    PROGRAM
    2.55
     PROGRAM
    2.54
    Activations Density 0.052%

    No Known Activations