© 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. 8200
    Prev
    Next
    INDEX
    Explanations

    expressions of social interactions and personal 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
     diurnal
    -0.35
    上门
    -0.33
     living
    -0.32
    readdir
    -0.30
     visitas
    -0.29
    LETTER
    -0.29
     daily
    -0.29
     hidup
    -0.29
     polymer
    -0.29
    現在は
    -0.29
    POSITIVE LOGITS
     chatting
    0.96
     chatted
    0.90
     chatter
    0.83
     loudly
    0.83
     whispering
    0.79
     overheard
    0.79
     chattering
    0.79
     conversing
    0.79
     giggling
    0.78
     conversation
    0.78
    Activations Density 0.511%

    No Known Activations