© 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. 20-GEMMASCOPE-RES-16K
    11. 6236
    Prev
    Next
    INDEX
    Explanations

    formatting elements and special characters in a text

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

    Code snippets or HTML fragments

    np_acts-logits-general · gemini-2.0-flash

    assembly, version, Ryu, CBS

    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
    withIdentifier
    -0.57
    enumi
    -0.57
    bitField
    -0.57
    createCanvas
    -0.52
    ITUTE
    -0.51
    éez
    -0.49
    mişti
    -0.45
    WithIdentifier
    -0.44
    ;->
    -0.43
     ·
    -0.43
    POSITIVE LOGITS
     AssemblyCompany
    0.71
     ivelany
    0.64
     CreateTagHelper
    0.61
     Templar
    0.59
     siguran
    0.58
     gawas
    0.58
     lenker
    0.57
    Portály
    0.55
     tartalomajánló
    0.54
    ThroughAttribute
    0.53
    Activations Density 0.019%

    No Known Activations