© 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. 5-GEMMASCOPE-RES-16K
    11. 6952
    Prev
    Next
    INDEX
    Explanations

    references to female characters, particularly strong or empowered women, in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     himself
    -0.68
    Grandpa
    -0.60
    limus
    -0.60
    父子
    -0.60
    __":
    -0.59
     Paglinawan
    -0.58
    łem
    -0.57
    叔叔
    -0.57
     boyhood
    -0.56
    وفاته
    -0.54
    POSITIVE LOGITS
     herself
    1.22
     lady
    1.21
     Lady
    1.14
     LADY
    1.12
     actresses
    1.12
     ladies
    1.11
     goddess
    1.10
    Lady
    1.08
     bint
    1.05
     girls
    1.04
    Activations Density 0.405%

    No Known Activations