© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 413
    Prev
    Next
    INDEX
    Explanations

    the mention of specific individuals and their significance in a context

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

    specific characters or symbols in the text

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

    web automation errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Попис
    -0.60
    Autres
    -0.58
    ///</
    -0.54
     دیکھیے
    -0.51
    yntaxException
    -0.51
    ativement
    -0.51
    Geplaatst
    -0.51
    Демографія
    -0.50
     sobie
    -0.50
    gestone
    -0.50
    POSITIVE LOGITS
    DataAnnotations
    0.84
     TextInputType
    0.81
    GrantedAuthority
    0.70
    ynb
    0.69
    NamedQuery
    0.66
    PerformLayout
    0.65
     Patrice
    0.64
     насељу
    0.63
    الإنجليزية
    0.62
     behö
    0.62
    Activations Density 0.067%

    No Known Activations