© 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. 40-GEMMASCOPE-RES-16K
    11. 6519
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fi
    -0.64
     Fl
    -0.59
     Fin
    -0.59
     Fil
    -0.58
     Fic
    -0.57
     File
    -0.56
     Field
    -0.56
     Form
    -0.56
     Fo
    -0.55
     Fir
    -0.55
    POSITIVE LOGITS
    f
    0.70
    from
    0.67
    far
    0.66
    fat
    0.63
    false
    0.61
    fa
    0.61
    fing
    0.60
    father
    0.59
    fire
    0.59
    fo
    0.59
    Activations Density 1.074%

    No Known Activations