© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9665
    Prev
    Next
    INDEX
    Explanations

    verbs related to shouting or vocal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    making sounds

    np_acts-logits-general · gemini-2.0-flash

    loud vocalizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.73
    ntos
    -0.61
    
    -0.59
    Хьажоргаш
    -0.57
    NewUrlParser
    -0.56
     للاسماء
    -0.54
    DebuggerNonUser
    -0.54
    IActionResult
    -0.54
    cèse
    -0.53
    Avon
    -0.52
    POSITIVE LOGITS
     loudly
    0.87
    AddTagHelper
    0.83
     loud
    0.78
     Scre
    0.73
     aloud
    0.70
     loudest
    0.70
    PerformLayout
    0.70
     louder
    0.69
     screaming
    0.69
    Scre
    0.68
    Activations Density 0.169%

    No Known Activations