© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 2550
    Prev
    Next
    INDEX
    Explanations

    positive descriptors and experiences related to food, social gatherings, and creative works

    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
    dafx
    -0.60
    expandindo
    -0.59
    UserScript
    -0.57
    
    -0.56
     հղումներ
    -0.52
    喽
    -0.51
     gyhoeddwyd
    -0.50
     protoimpl
    -0.49
    UObject
    -0.49
    principalColumn
    -0.49
    POSITIVE LOGITS
     considering
    0.89
     especially
    0.84
    considering
    0.79
     ngl
    0.74
     compared
    0.73
     indeed
    0.72
    especially
    0.71
     imo
    0.68
     considerando
    0.68
     Especially
    0.67
    Activations Density 0.220%

    No Known Activations