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. 6021
    Prev
    Next
    INDEX
    Explanations

    terms related to climate change, carbon emissions, and environmental issues

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

    following prepositions

    np_acts-logits-general · gemini-2.0-flash

    archaic spelling of words

    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
     I
    -0.57
    WebElementEntity
    -0.55
     E
    -0.53
     $
    -0.52
     El
    -0.52
     M
    -0.51
     T
    -0.51
     Sar
    -0.50
    si
    -0.50
     
    -0.49
    POSITIVE LOGITS
     itſelf
    1.21
     myſelf
    0.97
    ſelf
    0.94
    ſelves
    0.92
     faſt
    0.92
     houſe
    0.92
     ſtate
    0.90
     leaſt
    0.87
     iſt
    0.86
     auffi
    0.86
    Activations Density 0.603%

    No Known Activations