© 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. 35-GEMMASCOPE-RES-16K
    11. 13904
    Prev
    Next
    INDEX
    Explanations

    phrases related to feelings of connection and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pò
    -0.69
     لئے
    -0.68
     programme
    -0.65
    ichè
    -0.63
     Javascript
    -0.60
     programmes
    -0.59
     sulphur
    -0.59
    programme
    -0.59
     formulae
    -0.58
     Palae
    -0.58
    POSITIVE LOGITS
     theater
    1.05
     gray
    0.97
     Theater
    0.94
    theater
    0.91
    Theater
    0.91
    gray
    0.90
     fiber
    0.89
     toward
    0.88
     jewelry
    0.85
     canceled
    0.84
    Activations Density 1.592%

    No Known Activations