© 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. 22-GEMMASCOPE-RES-16K
    11. 6284
    Prev
    Next
    INDEX
    Explanations

    references to professions or roles associated with service or expertise

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

    Follows "are" or "were"

    np_acts-logits-general · gemini-2.0-flash

    past participles and adjectives

    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
     a
    -0.69
     seorang
    -0.59
     an
    -0.59
     someone
    -0.56
     seseorang
    -0.53
     démocr
    -0.51
     een
    -0.48
     একটি
    -0.48
     sebuah
    -0.48
     one
    -0.47
    POSITIVE LOGITS
     themselves
    1.10
    themselves
    1.03
     themſelves
    1.03
     yourselves
    1.00
     nahilalakip
    0.99
     scattered
    0.90
     estekak
    0.87
     raiſ
    0.86
     unanimous
    0.84
     strangers
    0.83
    Activations Density 0.260%

    No Known Activations