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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 12326
    Prev
    Next
    INDEX
    Explanations

    financial figures and data related to imports, exports, and economic impact

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

    preceding locations, areas, or organizations

    np_acts-logits-general · gemini-2.0-flash

    areas affected by drought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.58
    省市镇
    -0.56
    PreferredItem
    -0.55
    posedge
    -0.53
    出版年
    -0.53
     ostavi
    -0.49
    shadowOffset
    -0.49
    Trivia
    -0.49
     удо
    -0.49
    
    -0.48
    POSITIVE LOGITS
     dependent
    0.74
     reliant
    0.73
     affected
    0.72
    dependent
    0.69
     dependency
    0.65
     normally
    0.65
     dependence
    0.64
     Dependent
    0.64
    normally
    0.61
     dependant
    0.60
    Activations Density 0.423%

    No Known Activations