© 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. 18-GEMMASCOPE-RES-16K
    11. 9561
    Prev
    Next
    INDEX
    Explanations

    expressions related to concern and worry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "worry" or its inflections

    np_acts-logits-general · gemini-2.0-flash

    worry about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Xna
    -0.66
    XmlEnum
    -0.58
    ืน
    -0.57
    باس
    -0.53
    zések
    -0.51
    digm
    -0.51
    rapment
    -0.51
    AdapterView
    -0.50
    statin
    -0.50
    erokee
    -0.50
    POSITIVE LOGITS
     Worry
    1.36
     worry
    1.33
    worry
    1.30
     worries
    1.23
     worrying
    1.21
     worried
    1.02
     fret
    0.82
     preoc
    0.81
     preocupes
    0.78
    orry
    0.77
    Activations Density 0.056%

    No Known Activations