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. 3-GEMMASCOPE-RES-16K
    6. 10039
    Prev
    Next
    INDEX
    Explanations

    repeated references to the term "single."

    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
    
    -0.69
     ligiloj
    -0.67
    abetes
    -0.65
     laurels
    -0.64
    WebControls
    -0.64
    AddTagHelper
    -0.61
    רושלים
    -0.57
    IsContent
    -0.57
    OGND
    -0.57
    uluk
    -0.57
    POSITIVE LOGITS
      (
    0.52
     freakin
    0.50
    ://"
    0.50
    tonsoft
    0.49
    IsMutable
    0.49
     way
    0.48
    fucking
    0.48
     travaillons
    0.47
    Prä
    0.45
    bný
    0.45
    Activations Density 0.258%

    No Known Activations