© 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. 2581
    Prev
    Next
    INDEX
    Explanations

    words associated with prevention and protection measures

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

    "prevent" and its synonyms

    np_acts-logits-general · gemini-2.0-flash

    preventing future harm

    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
     disparu
    -0.58
    Autoritní
    -0.58
    protoimpl
    -0.57
     autorytatywna
    -0.56
     nowhere
    -0.55
    scryfall
    -0.54
    GroupLayout
    -0.52
    dited
    -0.52
    uarts
    -0.51
     chi̍t
    -0.51
    POSITIVE LOGITS
     possible
    1.06
     future
    1.02
     further
    1.01
     potential
    0.96
     unnecessary
    0.95
    possible
    0.94
     futuros
    0.92
    further
    0.91
    future
    0.90
     Possible
    0.89
    Activations Density 0.373%

    No Known Activations