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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 13740
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to networking and communication technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.87
     ligiloj
    -0.86
     Roskov
    -0.83
    :✨
    -0.79
     kasarigan
    -0.77
    存于互联网档案馆
    -0.76
    ⓧ
    -0.76
    MLLoader
    -0.76
     defaultstate
    -0.76
    Datuak
    -0.74
    POSITIVE LOGITS
     internet
    0.69
     Internet
    0.67
    dns
    0.62
    Internet
    0.59
    DNS
    0.57
    インターネット
    0.55
    internet
    0.54
     psycopg
    0.51
    inet
    0.51
     computer
    0.51
    Activations Density 0.630%

    No Known Activations