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. 10233
    Prev
    Next
    INDEX
    Explanations

    the word "may" and its variations, indicating uncertainty or possibility

    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
    Armand
    -0.57
     Armand
    -0.55
     وض
    -0.55
     rene
    -0.54
    totta
    -0.54
    Bullshit
    -0.53
    藹
    -0.53
     Huber
    -0.53
     trụ
    -0.52
     Ehr
    -0.52
    POSITIVE LOGITS
     may
    2.79
    may
    2.37
     MAY
    2.27
     might
    2.24
    MAY
    2.06
    May
    1.94
    might
    1.93
     May
    1.86
     Might
    1.81
    Might
    1.74
    Activations Density 0.096%

    No Known Activations