Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15574
    Prev
    Next
    INDEX
    Explanations

    references to female characters or pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.91
     raiſ
    -0.87
     Efq
    -0.87
     Houſe
    -0.85
     againſt
    -0.83
     cauſe
    -0.81
     uſe
    -0.79
     itſelf
    -0.77
     purpoſe
    -0.76
    נטרנט
    -0.76
    POSITIVE LOGITS
     her
    1.79
     his
    1.51
     Her
    1.43
     HER
    1.33
    her
    1.29
    Her
    1.28
     she
    1.26
     His
    1.17
     HIS
    1.15
    she
    1.09
    Activations Density 0.148%

    No Known Activations