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. 3087
    Prev
    Next
    INDEX
    Explanations

    concepts related to existence and spirituality on Earth

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

    the planet "Earth"

    np_acts-logits-general · gemini-2.0-flash

    on earth

    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
    TabIndex
    -0.62
    Семья
    -0.51
    anches
    -0.49
    (")");
    -0.49
    Билгалдахарш
    -0.48
     BoxFit
    -0.47
    stals
    -0.47
    НИЙ
    -0.47
    ligo
    -0.47
    _^
    -0.46
    POSITIVE LOGITS
     earth
    2.51
     Earth
    2.50
    Earth
    2.25
    earth
    2.19
     EARTH
    2.16
    EARTH
    1.87
     planet
    1.65
     earthly
    1.63
     earths
    1.55
     Planet
    1.43
    Activations Density 0.196%

    No Known Activations