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. 5134
    Prev
    Next
    INDEX
    Explanations

    expressions related to events and changes over time

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

    time or recent events

    np_acts-logits-general · gemini-2.0-flash

    events culminating or concluding

    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
    *>(
    -0.56
    expandindo
    -0.53
     dataSnapshot
    -0.52
     därför
    -0.51
    USING
    -0.51
    HasKey
    -0.50
    ίναι
    -0.49
     getItemCount
    -0.48
    ModelAdmin
    -0.47
    вайтесь
    -0.47
    POSITIVE LOGITS
     puisque
    0.82
     courtesy
    0.76
    courtesy
    0.72
    PerformLayout
    0.71
     cortesía
    0.69
     כאשר
    0.69
    AlterField
    0.67
     culminated
    0.67
     puisqu
    0.66
     thanks
    0.66
    Activations Density 0.389%

    No Known Activations