© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5407
    Prev
    Next
    INDEX
    Explanations

    key scientific terminology related to the atmosphere and environmental 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
    principalTable
    -0.48
     AssemblyCulture
    -0.43
     beſ
    -0.40
    arkhand
    -0.38
    AntiForgeryToken
    -0.38
    nehin
    -0.37
     akad
    -0.36
    Déc
    -0.36
    tomans
    -0.36
     Gher
    -0.35
    POSITIVE LOGITS
     gaps
    2.25
     gap
    2.25
     holes
    2.22
     hole
    2.16
     Gaps
    1.91
    gaps
    1.83
    gap
    1.82
    holes
    1.81
     Gap
    1.81
    Gap
    1.80
    Activations Density 1.131%

    No Known Activations