© 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. 4782
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptors of size or severity

    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
     Enough
    -0.75
    adaptiveStyles
    -0.73
    Sufficient
    -0.72
     sufficient
    -0.71
     Sufficient
    -0.71
     otomatig
    -0.71
    sufficient
    -0.71
     enough
    -0.69
     suffisamment
    -0.68
     sufficiently
    -0.68
    POSITIVE LOGITS
     finalement
    0.52
    actually
    0.47
     actually
    0.47
     înc
    0.44
     sounding
    0.43
     egentligen
    0.43
    Actually
    0.40
     lately
    0.40
     Actually
    0.40
     ACTUALLY
    0.38
    Activations Density 0.353%

    No Known Activations