© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9512
    Prev
    Next
    INDEX
    Explanations

    references to the concept of life on Earth

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

    "on Earth" or related to the Earth

    np_acts-logits-general · gemini-2.0-flash

    on earth or planet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.57
    ConstraintMaker
    -0.53
     Beek
    -0.51
    γμα
    -0.50
    pDialog
    -0.49
    óstico
    -0.49
     EdgeInsets
    -0.49
    原始内容存档于
    -0.48
    amerikanischer
    -0.48
    étaro
    -0.48
    POSITIVE LOGITS
     earth
    2.23
     Earth
    2.18
    Earth
    1.93
    earth
    1.85
     EARTH
    1.83
     planet
    1.72
    EARTH
    1.52
     Planet
    1.43
     earths
    1.40
    planet
    1.33
    Activations Density 0.198%

    No Known Activations