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. 20-GEMMASCOPE-RES-16K
    6. 15559
    Prev
    Next
    INDEX
    Explanations

    variations of the term "bra" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "bra" or "Bra"

    np_acts-logits-general · gemini-2.0-flash

    words beginning with bra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.78
    __':
    
    -0.75
    Portale
    -0.72
    providedIn
    -0.72
     EconPapers
    -0.70
    +#+#
    -0.69
    ).'
    -0.69
    __":
    
    -0.68
    帖最后由
    -0.66
     transférez
    -0.66
    POSITIVE LOGITS
     bra
    1.08
     Bra
    1.05
    Bra
    0.93
    bra
    0.84
     BRA
    0.79
     Bragg
    0.72
    BRA
    0.61
     bras
    0.60
     Bracket
    0.55
     Bray
    0.51
    Activations Density 0.065%

    No Known Activations