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. 20-GEMMASCOPE-RES-16K
    6. 11572
    Prev
    Next
    INDEX
    Explanations

    activities focused on spending time with family and friends

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

    calm, passive activities

    np_acts-logits-general · gemini-2.0-flash

    calmly enjoying activities

    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
    ctomy
    -0.53
     gyhoeddwyd
    -0.53
    gså
    -0.51
    NavController
    -0.50
     AppCompatTheme
    -0.50
    DoubleQuotes
    -0.49
    ARTER
    -0.49
    τως
    -0.48
    ULAR
    -0.48
    adə
    -0.48
    POSITIVE LOGITS
     peacefully
    0.95
     together
    0.85
     relaxing
    0.84
     surrounded
    0.84
     sambil
    0.81
     enjoying
    0.79
     watching
    0.78
     outdoors
    0.78
     leisurely
    0.76
     while
    0.74
    Activations Density 0.230%

    No Known Activations