© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 16072
    Prev
    Next
    INDEX
    Explanations

    references to romantic relationships and sexual experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的一部分
    -0.61
    shund
    -0.52
    تقاوى
    -0.50
    Халык
    -0.50
     pleinement
    -0.50
    lotte
    -0.48
    multirow
    -0.47
    Prze
    -0.47
    chaub
    -0.47
    BeginContext
    -0.47
    POSITIVE LOGITS
     everywhere
    1.26
     incessantly
    1.18
     nonstop
    1.10
    everywhere
    1.09
     constantly
    1.08
     galore
    1.05
     relentlessly
    1.01
     endlessly
    1.01
     willy
    1.01
     left
    0.99
    Activations Density 0.426%

    No Known Activations