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. 20-GEMMASCOPE-RES-16K
    6. 11801
    Prev
    Next
    INDEX
    Explanations

    references to Oracle and its features or related concepts

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

    Japanese honorifics or polite prefixes

    np_acts-logits-general · gemini-2.0-flash

    `su` followed by `es` or `face`, `ace` followed by `tabular` or `tracking`, `ご` followed by `不在`, `お` followed by `とな`

    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
     Baillargeon
    -0.58
    ContentAsync
    -0.53
     vôtre
    -0.52
     []:
    -0.52
    actionMode
    -0.51
     Audiodateien
    -0.50
    writerow
    -0.50
    rss
    -0.49
     Konkur
    -0.49
    tonsoft
    -0.49
    POSITIVE LOGITS
    :✨
    0.76
    apimachinery
    0.65
     MainAxisSize
    0.62
    Espèce
    0.59
    XmlEnum
    0.57
    UpInside
    0.56
    IPAC
    0.55
     intptr
    0.55
    نامه
    0.54
    InputBorder
    0.52
    Activations Density 0.091%

    No Known Activations