© 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. 14-GEMMASCOPE-RES-16K
    11. 195
    Prev
    Next
    INDEX
    Explanations

    phrases related to LGBTQ+ rights and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    зулта
    -0.43
    BagLayout
    -0.42
    rature
    -0.42
     betek
    -0.41
    큼
    -0.41
    aktur
    -0.41
     AssemblyCompany
    -0.41
    ofold
    -0.40
     CURIAM
    -0.40
    spesies
    -0.40
    POSITIVE LOGITS
     supposedly
    1.06
     allegedly
    0.92
     purported
    0.88
     supuestamente
    0.88
     ostensibly
    0.84
     apparently
    0.81
     prétend
    0.81
    apparently
    0.76
    supposed
    0.76
    Apparently
    0.75
    Activations Density 0.907%

    No Known Activations