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. 13424
    Prev
    Next
    INDEX
    Explanations

    dates and specific months mentioned in relation to events

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

    Months of the year following dates

    np_acts-logits-general · gemini-2.0-flash

    dates and events

    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
     المعيارى
    -0.68
     DialogResult
    -0.57
    BeginContext
    -0.54
     "^
    -0.53
    ريقة
    -0.51
    .',
    -0.50
    Архівовано
    -0.50
    ."]
    -0.49
    价比
    -0.49
    igshid
    -0.49
    POSITIVE LOGITS
    :✨
    0.67
    ंदीखरीदारी
    0.62
     aught
    0.58
    ???:
    0.58
     disambiguazione
    0.58
     onwards
    0.55
     "..\..\..\
    0.54
     idem
    0.54
     Theſe
    0.54
    ude
    0.53
    Activations Density 0.216%

    No Known Activations