© 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. 20-GEMMASCOPE-RES-16K
    11. 7769
    Prev
    Next
    INDEX
    Explanations

    terms related to fear and anxiety

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

    the emotion of fear

    np_acts-logits-general · gemini-2.0-flash

    fear, scared, and panic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.56
     Anspruch
    -0.50
    :✨
    -0.48
     nonUne
    -0.47
    mergeFrom
    -0.47
     soddis
    -0.46
    Referències
    -0.46
     StringTokenizer
    -0.46
     שוליים
    -0.46
     keterangan
    -0.45
    POSITIVE LOGITS
     fear
    3.05
     fears
    2.74
    fear
    2.57
     Fear
    2.53
    Fear
    2.46
     fearful
    2.39
     feared
    2.33
     FEAR
    2.31
     afraid
    2.30
     fearing
    2.27
    Activations Density 0.540%

    No Known Activations