© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14841
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to approval or value judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aguda
    -0.52
    DeleteCommand
    -0.48
     Lambert
    -0.47
     hot
    -0.46
    Ecc
    -0.45
    
    -0.45
    り返
    -0.45
    vezető
    -0.45
    /******/
    -0.45
     financières
    -0.43
    POSITIVE LOGITS
    ization
    1.70
    化
    1.57
    isation
    1.50
    ized
    1.36
    izing
    1.35
     hóa
    1.27
    IZATION
    1.21
    izations
    1.21
    化的
    1.19
    ize
    1.18
    Activations Density 0.373%

    No Known Activations