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. 16-GEMMASCOPE-RES-16K
    6. 14999
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to statutes of limitations

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

    "N.J." abbreviations

    np_acts-logits-general · gemini-2.0-flash

    NJ citations and Jersey

    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
     defaultstate
    -0.62
     Spokane
    -0.60
    sizePolicy
    -0.57
    wien
    -0.57
     Alberta
    -0.56
    Alberta
    -0.56
    PyExc
    -0.55
     Seattle
    -0.54
     Edmonton
    -0.54
     BYU
    -0.54
    POSITIVE LOGITS
     NJ
    1.03
    NJ
    0.91
     Jersey
    0.86
     Rutgers
    0.84
     Newark
    0.84
     nj
    0.82
    Jersey
    0.80
     JERSEY
    0.76
     Monmouth
    0.72
    Newark
    0.69
    Activations Density 0.452%

    No Known Activations