Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4176
    Prev
    Next
    INDEX
    Explanations

    the start of a new section or paragraph in technical documents

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

    Comes before initials, numbers, or bracketed names

    np_acts-logits-general · gemini-2.0-flash

    surnames

    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
     defStyleAttr
    -0.65
     acolo
    -0.47
    Билгалдахарш
    -0.47
    GEBURTSDATUM
    -0.47
     Eſ
    -0.47
     Datenschutzer
    -0.47
     neutre
    -0.46
     supuestamente
    -0.46
     Tetrahedron
    -0.44
     Morena
    -0.44
    POSITIVE LOGITS
     Zhou
    0.69
     Wang
    0.69
     Jiang
    0.64
     Liu
    0.64
     Huang
    0.63
    tershire
    0.61
     Zhang
    0.60
     Qin
    0.59
     Zheng
    0.58
     Ahmed
    0.58
    Activations Density 0.438%

    No Known Activations