© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3918
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Mrs." and references to female characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     codes
    -0.61
    setCode
    -0.57
     brin
    -0.57
     لام
    -0.57
     Code
    -0.57
     tools
    -0.56
     Tool
    -0.56
     tool
    -0.55
     gir
    -0.55
     CODE
    -0.55
    POSITIVE LOGITS
    Properties
    1.01
    XmlAccessorType
    0.82
    PROPERTIES
    0.77
     WebDriverWait
    0.77
    properties
    0.77
     characterized
    0.76
     désolés
    0.74
     characterised
    0.73
    LookAnd
    0.71
     characterizes
    0.70
    Activations Density 0.104%

    No Known Activations