© 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. 3-GEMMASCOPE-RES-16K
    6. 2033
    Prev
    Next
    INDEX
    Explanations

    references to the word "Bra" and its variations or derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Burke
    -0.71
     Jagger
    -0.68
     Felton
    -0.66
     DICE
    -0.65
     Burr
    -0.65
     Burroughs
    -0.64
    genstein
    -0.64
    usercontent
    -0.61
     ripple
    -0.59
    Burke
    -0.59
    POSITIVE LOGITS
     Bra
    2.85
    Bra
    2.82
     bra
    2.81
    bra
    2.61
     BRA
    2.24
    BRA
    1.87
     bras
    1.84
    Bras
    1.53
     Braxton
    1.51
     Bras
    1.49
    Activations Density 0.085%

    No Known Activations