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-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 1274
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to astronomical objects and phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SceneManagement
    -0.34
    Distribuzione
    -0.32
    éndole
    -0.30
     abger
    -0.28
    #![
    -0.28
     matri
    -0.28
     JIT
    -0.28
     acel
    -0.27
    borderRadius
    -0.27
     UIC
    -0.27
    POSITIVE LOGITS
     astronomers
    1.12
     telescopes
    1.09
     telescope
    1.09
     astronomer
    1.03
     astronomy
    1.03
     astronomical
    0.99
     Astronomy
    0.98
     Astronomical
    0.97
     Telescope
    0.94
     observatory
    0.94
    Activations Density 0.317%

    No Known Activations