© 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. 24-GEMMASCOPE-RES-16K
    11. 14214
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and the presence of specific narrative elements in text

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

    Text before a period

    np_acts-logits-general · gemini-2.0-flash

    places to visit and explore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     using
    -0.48
    apimachinery
    -0.46
    reszcie
    -0.43
     court
    -0.42
    using
    -0.41
    ollectionView
    -0.41
     >=",
    -0.40
    toral
    -0.40
     Indem
    -0.40
     same
    -0.40
    POSITIVE LOGITS
     Located
    1.09
     Nearby
    1.08
    Located
    1.03
     Situated
    1.01
    Nearby
    1.00
    Situated
    0.90
     Stroll
    0.89
    Visitors
    0.88
     Spend
    0.87
    Spend
    0.86
    Activations Density 0.139%

    No Known Activations