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. 15-GEMMASCOPE-RES-16K
    6. 4504
    Prev
    Next
    INDEX
    Explanations

    issues related to international relations and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     color
    -0.57
     folks
    -0.50
     we
    -0.50
    Behavior
    -0.49
     Oklahoma
    -0.47
     favor
    -0.46
     Image
    -0.46
     Behavior
    -0.46
     Behavioral
    -0.45
     statewide
    -0.45
    POSITIVE LOGITS
     envisaged
    1.10
     resourceCulture
    1.10
    الحياه
    1.09
    TagMode
    1.00
     colourless
    0.96
     diarrhoea
    0.95
     multilateral
    0.95
    flav
    0.94
     emphasised
    0.93
     autorytatywna
    0.93
    Activations Density 0.479%

    No Known Activations