© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 6663
    Prev
    Next
    INDEX
    Explanations

    references to stem flow and related measurements in ecological or forestry contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Form
    -0.57
     f
    -0.57
     file
    -0.57
     Fields
    -0.57
     field
    -0.56
     fl
    -0.56
     File
    -0.56
     fil
    -0.56
     fi
    -0.56
     frame
    -0.56
    POSITIVE LOGITS
    f
    0.75
    fu
    0.61
    few
    0.60
    far
    0.60
    fat
    0.60
    from
    0.59
    fo
    0.59
    fruit
    0.58
    fa
    0.57
    fame
    0.57
    Activations Density 1.279%

    No Known Activations