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. 24-GEMMASCOPE-RES-16K
    6. 14000
    Prev
    Next
    INDEX
    Explanations

    references to time travel and its implications

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

    Following "the" and preceding possible objects

    np_acts-logits-general · gemini-2.0-flash

    the specific noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.81
     ویکی‌پدی
    -0.69
     exemples
    -0.62
    揄
    -0.58
    igshid
    -0.53
    addCriterion
    -0.53
    islative
    -0.53
     désolés
    -0.52
     exemplos
    -0.52
    grà
    -0.52
    POSITIVE LOGITS
     secret
    0.98
     treasure
    0.93
     artifact
    0.85
     amulet
    0.84
    secret
    0.83
     locket
    0.81
     relic
    0.77
    treasure
    0.74
     elixir
    0.74
     secrets
    0.73
    Activations Density 0.375%

    No Known Activations