© 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. 5433
    Prev
    Next
    INDEX
    Explanations

    references to the moon and its various aspects or interpretations

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

    "moon" or "moons"

    np_acts-logits-general · gemini-2.0-flash

    moon and astro related terms

    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
    le
    -0.55
    a
    -0.49
     arqu
    -0.47
     Coronado
    -0.46
     parar
    -0.42
    厥
    -0.40
    To
    -0.39
    est
    -0.39
    B
    -0.39
    رق
    -0.39
    POSITIVE LOGITS
    OGND
    1.03
     Савезне
    0.88
     astronauts
    0.87
     moons
    0.84
    typeorm
    0.84
    principalColumn
    0.83
    MLLoader
    0.83
    abestanden
    0.82
    🌖
    0.81
    ReusableCell
    0.81
    Activations Density 0.227%

    No Known Activations