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. 14980
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibility and careful use of language

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

    Adverbs describing careful or correct actions

    np_acts-logits-general · gemini-2.0-flash

    how something is handled or managed

    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
     متعلقه
    -0.83
     transfieras
    -0.77
     nahilalakip
    -0.73
    parsedMessage
    -0.71
    ReusableCell
    -0.70
    ⓧ
    -0.70
     незавершена
    -0.69
    GEBURTSDATUM
    -0.68
     GenerationType
    -0.68
    حياتها
    -0.68
    POSITIVE LOGITS
     very
    0.71
     fairly
    0.70
     efficiently
    0.67
     properly
    0.66
     effectively
    0.66
     adequately
    0.64
     robust
    0.63
     creatively
    0.63
     comprehensively
    0.61
    อย่าง
    0.61
    Activations Density 0.771%

    No Known Activations