© 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 EvalsExportsinterp-engineNEWAPI 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. 7210
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the significance or impact of research and findings

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

    preceding measurements/impact

    np_acts-logits-general · gemini-2.0-flash

    large magnitude or extent

    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
     complètement
    -0.54
     entièrement
    -0.53
     penuh
    -0.53
     mauva
    -0.51
     maravillosas
    -0.50
    ish
    -0.50
     sytu
    -0.49
     sufficiently
    -0.49
    AutoScale
    -0.49
     endless
    -0.49
    POSITIVE LOGITS
     ligiloj
    0.84
     emphasis
    0.82
    WriteBarrier
    0.81
    writeFieldEnd
    0.70
    __*/
    0.69
     resemblance
    0.68
     influence
    0.68
     overlap
    0.66
    UrlResolution
    0.65
    mybatisplus
    0.64
    Activations Density 0.556%

    No Known Activations