© 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. 18-GEMMASCOPE-RES-16K
    11. 2005
    Prev
    Next
    INDEX
    Explanations

    terms that indicate recognition and acclaim in various contexts

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

    Prepositions followed by nouns or pronouns

    np_acts-logits-general · gemini-2.0-flash

    groups of people or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.61
    #![
    -0.58
    findpost
    -0.57
    Rptr
    -0.56
    $_['
    -0.55
    LLocation
    -0.53
     елның
    -0.52
    BufferException
    -0.52
     Chwiliwch
    -0.51
    inį
    -0.50
    POSITIVE LOGITS
     everyone
    0.90
     circles
    0.87
     everybody
    0.86
     kalangan
    0.78
     industry
    0.78
     fans
    0.76
    everyone
    0.75
     onlookers
    0.74
    everybody
    0.74
     audiences
    0.73
    Activations Density 0.267%

    No Known Activations