© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 11073
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <%=
    -0.51
    ว์
    -0.51
    iecie
    -0.51
     đại
    -0.51
    ศาสตร์
    -0.50
     Peters
    -0.50
     P
    -0.48
    IMDG
    -0.48
    mezzo
    -0.48
    дые
    -0.48
    POSITIVE LOGITS
     frankly
    0.93
     honestly
    0.86
    Honestly
    0.86
     Honestly
    0.80
    honestly
    0.77
    Frankly
    0.76
    really
    0.74
     really
    0.73
    ScopeManager
    0.73
     admit
    0.71
    Activations Density 0.127%

    No Known Activations