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. 16318
    Prev
    Next
    INDEX
    Explanations

    terms and expressions related to fear and anxiety

    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
    ionais
    -0.78
    كذا
    -0.74
    IMENTAL
    -0.71
     McKe
    -0.69
     Gough
    -0.69
     initComponents
    -0.69
    wój
    -0.68
     appuntamento
    -0.68
    ostomy
    -0.67
     nahilalakip
    -0.65
    POSITIVE LOGITS
     fear
    3.29
     Fear
    3.07
    fear
    2.97
     FEAR
    2.93
    Fear
    2.87
     fears
    2.76
     Fears
    2.37
     feared
    2.29
     fearing
    2.11
     fearful
    2.00
    Activations Density 0.038%

    No Known Activations