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. 13001
    Prev
    Next
    INDEX
    Explanations

    references to medical experiences or conditions

    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
     للمعارف
    -0.66
    abetes
    -0.61
    Vanjske
    -0.60
    armament
    -0.60
    TAWA
    -0.60
     tebal
    -0.57
     homenaje
    -0.56
    мерть
    -0.55
     Зачем
    -0.54
     kawa
    -0.54
    POSITIVE LOGITS
     experiencing
    1.41
     undergone
    1.38
     experienced
    1.37
     undergo
    1.31
     undergoes
    1.29
     undergoing
    1.20
    experienced
    1.20
     suffered
    1.19
     underwent
    1.17
     mengalami
    1.09
    Activations Density 0.349%

    No Known Activations