© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1725
    Prev
    Next
    INDEX
    Explanations

    elements related to social interactions and gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WTF
    -0.70
     fucking
    -0.68
    Fucking
    -0.67
    Damn
    -0.66
     essentially
    -0.66
    Shit
    -0.63
    WTF
    -0.63
     Damn
    -0.63
     Wtf
    -0.62
    fuck
    -0.62
    POSITIVE LOGITS
     yummy
    0.97
     mommy
    0.96
     Mommy
    0.95
    Mommy
    0.81
     naughty
    0.80
     Mummy
    0.79
     playtime
    0.77
     daddy
    0.74
     mummy
    0.74
    mommy
    0.71
    Activations Density 0.187%

    No Known Activations