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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15679
    Prev
    Next
    INDEX
    Explanations

    instances of discussion or storytelling related to personal or team experiences

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

    after commas and periods

    np_acts-logits-general · gemini-2.0-flash

    names of people and places

    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
     Perſ
    -0.91
     Reſ
    -0.85
     Diſ
    -0.85
     Inſ
    -0.80
     Conſ
    -0.80
     Majefty
    -0.77
     Houſe
    -0.76
     Anſ
    -0.76
     ſche
    -0.75
     Perfon
    -0.74
    POSITIVE LOGITS
     Mc
    0.68
     Smith
    0.67
     Johnson
    0.65
     Williams
    0.63
     Jones
    0.62
    Mc
    0.61
     van
    0.60
     Singh
    0.59
     כה
    0.58
     Baillargeon
    0.57
    Activations Density 2.532%

    No Known Activations