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. 22-GEMMASCOPE-RES-16K
    6. 3364
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions and personal feelings

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

    before negative emotion adjectives

    np_acts-logits-general · gemini-2.0-flash

    states of unease or confusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     industriale
    -0.57
     mismanagement
    -0.56
     rând
    -0.56
     asmen
    -0.52
     muligt
    -0.52
     accompagne
    -0.51
    rollup
    -0.51
     umiejęt
    -0.50
    IsNotNull
    -0.49
    ėjimas
    -0.49
    POSITIVE LOGITS
     stressed
    1.19
     excited
    1.14
     upset
    1.12
     nervous
    1.08
     embarrassed
    1.05
     frustrated
    1.04
     annoyed
    1.03
     bored
    1.01
     confused
    1.00
     depressed
    0.99
    Activations Density 0.249%

    No Known Activations