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. 6-GEMMASCOPE-RES-16K
    6. 4298
    Prev
    Next
    INDEX
    Explanations

    references to Earth and planetary concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Amos
    -0.70
    iegler
    -0.69
    orious
    -0.69
     المعيارى
    -0.68
    AddWithValue
    -0.65
    estyles
    -0.63
    quehanna
    -0.61
     vog
    -0.60
    toggler
    -0.60
    RenderAtEndOf
    -0.60
    POSITIVE LOGITS
     Earth
    2.20
     EARTH
    2.06
    Earth
    2.00
     earth
    1.98
    EARTH
    1.87
    earth
    1.77
     Erde
    1.57
     earths
    1.54
     Зем
    1.22
     Tierra
    1.15
    Activations Density 0.053%

    No Known Activations