© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 2691
    Prev
    Next
    INDEX
    Explanations

    references to players' skills and performance metrics

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

    Follows names, often athlete's last names

    np_acts-logits-general · gemini-2.0-flash

    basketball player names and roles

    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
    tagHelperRunner
    -0.68
    complexContent
    -0.65
    ViewImports
    -0.56
     Autorizaciones
    -0.54
     dục
    -0.54
    ֲ
    -0.53
    ungsbedingungen
    -0.52
    MetaObject
    -0.51
    Reentrant
    -0.50
    Sparta
    -0.50
    POSITIVE LOGITS
    rungsseite
    0.66
     Conſ
    0.55
     propOrder
    0.54
     myſelf
    0.54
    vably
    0.53
    GraphicsUnit
    0.53
     Ingles
    0.53
     Anſ
    0.51
     Theſe
    0.51
    ContentAsync
    0.51
    Activations Density 0.138%

    No Known Activations