© 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. 7846
    Prev
    Next
    INDEX
    Explanations

    phrases and references to data and reporting

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

    "These" followed by various nouns

    np_acts-logits-general · gemini-2.0-flash

    These

    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
     épaules
    -0.75
     oreilles
    -0.71
     jambes
    -0.65
     lèvres
    -0.63
     genoux
    -0.63
     ongles
    -0.63
     blessés
    -0.62
     âmes
    -0.62
     Juifs
    -0.61
     églises
    -0.60
    POSITIVE LOGITS
     Theſe
    1.20
     kinds
    1.18
     sorts
    1.13
     guys
    1.06
     disambiguazione
    1.02
     '\\;'
    0.99
     these
    0.94
    NameInMap
    0.89
     nakalista
    0.89
    These
    0.87
    Activations Density 0.177%

    No Known Activations