© 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. 1911
    Prev
    Next
    INDEX
    Explanations

    second-person references indicating interest or engagement in an activity or topic

    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
     probably
    -0.63
    probably
    -0.61
     Probably
    -0.57
    Probably
    -0.56
     whoever
    -0.55
     почти
    -0.52
     rất
    -0.51
     almost
    -0.50
     presque
    -0.50
     every
    -0.49
    POSITIVE LOGITS
     anything
    0.89
     quelconque
    0.84
     any
    0.84
     truly
    0.81
    anything
    0.78
     jemals
    0.77
    truly
    0.76
     anywhere
    0.75
     sufficiently
    0.75
     ANYTHING
    0.75
    Activations Density 0.492%

    No Known Activations