© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3835
    Prev
    Next
    INDEX
    Explanations

    references to wealth and economic issues

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

    following the word "The"

    np_acts-logits-general · gemini-2.0-flash

    the followed by a concept

    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
     ivelany
    -0.73
     <>",
    -0.72
    こち
    -0.67
    ритори
    -0.66
    wieś
    -0.65
    IndentedString
    -0.64
    ManagedBean
    -0.63
    GeoNames
    -0.60
     Biôgrafia
    -0.58
    LogFactory
    -0.58
    POSITIVE LOGITS
     key
    1.47
     thing
    1.16
     reason
    1.12
     point
    1.11
     problem
    1.07
     trick
    1.07
     truth
    1.02
     fact
    1.02
     important
    1.02
     question
    0.99
    Activations Density 0.361%

    No Known Activations