© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 2454
    Prev
    Next
    INDEX
    Explanations

    expressions related to protection and security

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

    Protecting something

    np_acts-logits-general · gemini-2.0-flash

    protecting interests and property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -1.01
     autorytatywna
    -0.80
     ComVisible
    -0.76
     cherchés
    -0.75
    WithIOException
    -0.73
     kaarangay
    -0.72
    出版年
    -0.70
     الرياضيه
    -0.70
     ویکی‌پدیا
    -0.69
    usermodel
    -0.69
    POSITIVE LOGITS
     against
    0.90
     Against
    0.78
    against
    0.76
     precious
    0.74
     integrity
    0.71
    不被
    0.70
     interests
    0.70
    Against
    0.69
     rights
    0.68
     valuable
    0.67
    Activations Density 0.166%

    No Known Activations