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. 16262
    Prev
    Next
    INDEX
    Explanations

    instances of the word "none."

    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
    ward
    -0.61
     Wilma
    -0.58
    ạm
    -0.57
     kya
    -0.57
     Draper
    -0.57
    PasswordField
    -0.55
     buhay
    -0.55
    setTextSize
    -0.55
     Sawyer
    -0.55
     ਲਈ
    -0.55
    POSITIVE LOGITS
     none
    2.90
    none
    2.57
    None
    2.45
     None
    2.44
     NONE
    2.28
     ninguno
    2.09
    NONE
    2.07
     nessuno
    1.62
     nobody
    1.40
    nobody
    1.39
    Activations Density 0.043%

    No Known Activations