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. 17-GEMMASCOPE-RES-16K
    6. 505
    Prev
    Next
    INDEX
    Explanations

    references to international relationships and shipping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setof
    -0.42
    <eos>
    -0.41
    medi
    -0.39
    c
    -0.39
    weet
    -0.38
    HANDLER
    -0.38
    setti
    -0.37
    z
    -0.36
    l
    -0.36
    צ
    -0.36
    POSITIVE LOGITS
     abroad
    2.32
     overseas
    2.23
     foreign
    2.06
     Abroad
    2.06
     international
    1.89
    Overseas
    1.89
    foreign
    1.88
     Overseas
    1.81
    international
    1.77
     foreigners
    1.76
    Activations Density 0.391%

    No Known Activations