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. 12842
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal growth and self-reflection

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

    Sentences ending in a period

    np_acts-logits-general · gemini-2.0-flash

    foreign language phrases

    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
    anmoins
    -0.86
     EconPapers
    -0.85
    AndEndTag
    -0.82
    theless
    -0.80
     समीक्षक
    -0.77
     <=",
    -0.74
    */),
    -0.73
    bulaire
    -0.72
    WriteTagHelper
    -0.71
    ագրություններ
    -0.71
    POSITIVE LOGITS
     capables
    0.52
     every
    0.46
     bawat
    0.46
    America
    0.43
     namen
    0.43
     And
    0.42
    XtraGrid
    0.42
     America
    0.41
     işte
    0.40
    .
    0.40
    Activations Density 0.304%

    No Known Activations