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

    Neuronpedia

    Jacobian LensNEW
    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. 13390
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions and relationships

    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
    脚注の使い方
    -0.50
    ніципа
    -0.46
     Italijanski
    -0.45
     propOrder
    -0.43
    IVEREF
    -0.42
    RTSC
    -0.42
    Availability
    -0.42
     ويكيپيديا
    -0.41
     disambiguazione
    -0.41
    gbaar
    -0.41
    POSITIVE LOGITS
     treated
    0.91
     cared
    0.87
     protected
    0.84
     accommodated
    0.82
     supported
    0.81
     pam
    0.75
     entertained
    0.74
     nourished
    0.70
     Treated
    0.68
     nurtured
    0.68
    Activations Density 0.272%

    No Known Activations