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. 20-GEMMASCOPE-RES-16K
    6. 2387
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight significant challenges or issues in various contexts

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

    "a" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    a followed by status descriptor

    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
    BuildContext
    -0.58
    MigrationBuilder
    -0.56
    ifflin
    -0.53
    mtrl
    -0.52
    로운
    -0.51
    interopRequire
    -0.49
    SPONSORED
    -0.48
    snippet
    -0.47
    achery
    -0.45
    iocene
    -0.45
    POSITIVE LOGITS
     source
    0.88
    InputBorder
    0.75
    source
    0.71
     contributor
    0.70
     источник
    0.65
     fuente
    0.64
     hindrance
    0.63
     focus
    0.61
     topic
    0.61
    DrawerToggle
    0.60
    Activations Density 0.347%

    No Known Activations