Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 13793
    Prev
    Next
    INDEX
    Explanations

    references to specific atmospheric conditions or events relating to elevation and environmental impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Erişim
    -0.48
     red
    -0.45
    sendFile
    -0.44
    rawDesc
    -0.43
     adresse
    -0.43
     gr
    -0.42
     Red
    -0.42
     appelez
    -0.42
     miesięcy
    -0.41
     base
    -0.41
    POSITIVE LOGITS
     airspace
    0.82
     flown
    0.78
     skies
    0.74
     flew
    0.71
     flying
    0.70
     pigeons
    0.70
     artificiales
    0.70
     altitudes
    0.69
     kites
    0.68
     ornith
    0.67
    Activations Density 0.185%

    No Known Activations