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. 25-GEMMASCOPE-RES-16K
    6. 1694
    Prev
    Next
    INDEX
    Explanations

    words associated with the Ebola epidemic and its impact on public health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.64
    amation
    -0.58
    🫣
    -0.53
     unvaccinated
    -0.53
    🫠
    -0.52
    🫶
    -0.51
     jScrollPane
    -0.50
     متعلقه
    -0.49
    🪄
    -0.49
    Portály
    -0.48
    POSITIVE LOGITS
     containment
    0.69
    IntoConstraints
    0.65
     flattening
    0.64
     flatten
    0.63
    驰
    0.62
     venti
    0.61
     PPE
    0.60
     testing
    0.60
     hydroxy
    0.60
    PPE
    0.60
    Activations Density 0.170%

    No Known Activations