© 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. 36-GEMMASCOPE-RES-16K
    11. 7418
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "It" or variations indicating conclusions or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.66
     habet
    -0.58
     deſt
    -0.57
     indígen
    -0.57
     ſever
    -0.54
     étoient
    -0.54
     comigo
    -0.54
    parsedMessage
    -0.53
     itſelf
    -0.53
     uſed
    -0.53
    POSITIVE LOGITS
     beho
    0.54
     conceivable
    0.44
     important
    0.38
     ज्ञात
    0.38
     noteworthy
    0.37
     ضروری
    0.37
     suffices
    0.36
     cabe
    0.35
     evident
    0.34
    AppCompat
    0.34
    Activations Density 0.252%

    No Known Activations