© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 16108
    Prev
    Next
    INDEX
    Explanations

    mentions of complex diseases and their societal implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.72
    RegressionTest
    -0.69
     Infórmanos
    -0.68
    oredCriteria
    -0.66
     nahilalakip
    -0.66
    észetes
    -0.66
    Демографія
    -0.63
     ZEALAND
    -0.62
    RegistryLite
    -0.60
    ایج
    -0.59
    POSITIVE LOGITS
     operated
    0.48
     illet
    0.45
     ra
    0.44
    huri
    0.44
     surrounded
    0.43
    thenia
    0.43
     taken
    0.42
     quite
    0.42
    <
    0.42
    ipi
    0.41
    Activations Density 0.492%

    No Known Activations