© 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. 13170
    Prev
    Next
    INDEX
    Explanations

    references to articles, papers, and reports in academic or formal writing

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

    preceding "article", "paper", or "thesis"

    np_acts-logits-general · gemini-2.0-flash

    publication content

    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
     tweeting
    -0.55
    KommentareTeilen
    -0.54
    GOTREF
    -0.53
    writerow
    -0.51
    becomes
    -0.51
    śmy
    -0.50
     Verk
    -0.50
     ensuring
    -0.49
    elemField
    -0.49
    ِّف
    -0.49
    POSITIVE LOGITS
     contain
    0.99
     contains
    0.92
     outlines
    0.80
     contained
    0.80
    contains
    0.79
     dealt
    0.78
     deals
    0.75
     lists
    0.75
    contain
    0.74
     deal
    0.73
    Activations Density 0.608%

    No Known Activations