© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7854
    Prev
    Next
    INDEX
    Explanations

    the presence of specific numerical or coded formats in the text

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

    "'t", "'s", and "to"

    np_acts-logits-general · gemini-2.0-flash

    't contractions and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.95
    BibitemShut
    -0.75
    期刊论文
    -0.71
    AnchorStyles
    -0.69
    "],
    -0.68
    Espèce
    -0.67
    — 
    -0.67
    )._
    -0.66
    )__
    -0.64
    .。
    -0.63
    POSITIVE LOGITS
    <bos>
    0.80
    SuppressMessage
    0.65
    openzeppelin
    0.59
     isotopes
    0.59
     emeritus
    0.58
     initComponents
    0.58
    webElementXpaths
    0.54
     Emeritus
    0.53
     Olympedia
    0.53
     embassies
    0.52
    Activations Density 0.377%

    No Known Activations