© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15434
    Prev
    Next
    INDEX
    Explanations

    complex relationships involving socio-legal and psychological themes

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

    Adjectives ending in '-al' or '-ly'

    np_acts-logits-general · gemini-2.0-flash

    listing abstract domains and qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.75
     Protestantism
    -0.73
    indd
    -0.70
     vulgaires
    -0.69
    AndroidJUnit
    -0.67
     nahilalakip
    -0.65
     дописавши
    -0.64
    Cyfeiriadau
    -0.64
    Tracce
    -0.64
    bootstrapcdn
    -0.63
    POSITIVE LOGITS
     cultural
    0.72
     socio
    0.71
     psycho
    0.66
    ทาง
    0.63
     structural
    0.62
     political
    0.62
     financial
    0.60
     spatial
    0.59
     pys
    0.58
     spiritual
    0.58
    Activations Density 0.575%

    No Known Activations