© 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. 5
    Prev
    Next
    INDEX
    Explanations

    references to locations or placement

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

    occurrences of the word "in" and its context within sentences

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

    people in groups

    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
    ]")]
    -0.80
    itself
    -0.77
     itſelf
    -0.69
    مصادر
    -0.64
     itself
    -0.63
     Itself
    -0.59
     ninguém
    -0.55
    usermodel
    -0.55
    RequestMethod
    -0.53
     руке
    -0.52
    POSITIVE LOGITS
     whom
    1.07
     who
    1.07
    who
    0.81
    whom
    0.76
    تفصیلات
    0.75
     kteří
    0.73
     know
    0.70
     whose
    0.64
     quienes
    0.64
     Who
    0.64
    Activations Density 0.161%

    No Known Activations