Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 13008
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and sentiments related to personal feelings and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.90
    
    -0.83
     jsPsych
    -0.80
     Roskov
    -0.78
    __':
    
    -0.78
    клопе
    -0.75
    migrationBuilder
    -0.74
    DockStyle
    -0.74
     BorderRadius
    -0.73
    sizeCache
    -0.72
    POSITIVE LOGITS
    DRO
    0.56
     myself
    0.55
    feels
    0.53
     Gefühl
    0.51
     Feels
    0.50
     enjo
    0.49
    feel
    0.49
     feel
    0.48
    feeling
    0.48
     feeling
    0.47
    Activations Density 0.321%

    No Known Activations