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. 12101
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to equations and conditions

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

    Mathematical/scientific formulas with symbols

    np_acts-logits-general · gemini-2.0-flash

    $ k $-levels or plural slaves

    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
    userdetails
    -0.59
    Бахар
    -0.58
    cjon
    -0.57
     Vikipedi
    -0.55
    IsContent
    -0.54
    >−
    -0.54
    BagLayout
    -0.53
    contentLoaded
    -0.52
    :],
    -0.52
    ReusableCell
    -0.52
    POSITIVE LOGITS
     Standby
    0.51
    IVersion
    0.51
     shippuden
    0.50
     nth
    0.50
     Filho
    0.50
     dedu
    0.50
     Wp
    0.49
     Whigs
    0.48
     byz
    0.47
     Allende
    0.47
    Activations Density 1.046%

    No Known Activations