© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12677
    Prev
    Next
    INDEX
    Explanations

    references to Earth and related planetary terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.81
    Amos
    -0.80
    zepam
    -0.69
    ServiceModel
    -0.69
    rungsseite
    -0.69
    Արտաքին
    -0.69
     Prze
    -0.68
    toggler
    -0.67
    minecraftforge
    -0.67
     فريبيس
    -0.66
    POSITIVE LOGITS
     Earth
    1.78
     EARTH
    1.69
    EARTH
    1.59
    Earth
    1.58
     earth
    1.54
     Erde
    1.43
    earth
    1.35
     earths
    1.21
     Зем
    1.03
     earthly
    0.93
    Activations Density 0.050%

    No Known Activations