© 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. 22-GEMMASCOPE-RES-16K
    11. 391
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to statistical analysis and tests

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

    Mathematical theorem names

    np_acts-logits-general · gemini-2.0-flash

    mathematician names and their theorems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResponseWriter
    -0.65
     bershka
    -0.61
     nahilalakip
    -0.59
    makeText
    -0.59
    fjspx
    -0.54
     uſe
    -0.54
    skirts
    -0.53
    ◕
    -0.53
    wendigkeit
    -0.52
    SourceChecksum
    -0.52
    POSITIVE LOGITS
    ian
    0.84
    IAN
    0.73
    ův
    0.68
    iana
    0.67
    ntype
    0.64
    iano
    0.63
     type
    0.63
     himself
    0.62
     дописавши
    0.60
     theorem
    0.59
    Activations Density 0.608%

    No Known Activations