© 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. 1469
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or statistics related to rankings or scores

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

    Numbers followed by colons

    np_acts-logits-general · gemini-2.0-flash

    dates and years

    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
     GenerationType
    -0.71
     betweenstory
    -0.70
     otomatig
    -0.66
    AsStream
    -0.63
     ModelExpression
    -0.58
     ['$
    -0.57
     suivante
    -0.57
    Rebs
    -0.57
    ACHUSETTS
    -0.57
     disponibilités
    -0.56
    POSITIVE LOGITS
    BeginContext
    0.56
    hless
    0.51
    Personendaten
    0.49
    IonicModule
    0.48
    ben
    0.45
     order
    0.45
     compare
    0.44
    HttpEntity
    0.43
     Compare
    0.43
     گزارش
    0.42
    Activations Density 0.072%

    No Known Activations