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. 1587
    Prev
    Next
    INDEX
    Explanations

    requirements or actions related to submission processes

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

    preceding verbs in the infinitive form

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed by actions

    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
     vieta
    -0.46
     platí
    -0.43
    onAttach
    -0.43
    stęp
    -0.41
     generali
    -0.41
    出的
    -0.40
    Laughs
    -0.40
     célèbres
    -0.40
     Sociales
    -0.40
    Poloha
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.91
     المعيارى
    0.82
    出版年
    0.78
     الحره
    0.76
    Personensuche
    0.73
    abestanden
    0.71
    íslu
    0.70
    ksikon
    0.67
    gameserver
    0.67
    uxxxx
    0.66
    Activations Density 0.542%

    No Known Activations