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. 18-GEMMASCOPE-RES-16K
    6. 14545
    Prev
    Next
    INDEX
    Explanations

    phrases related to data privacy and security measures

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

    Data privacy and security

    np_acts-logits-general · gemini-2.0-flash

    data privacy and security

    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
     становника
    -0.67
    evos
    -0.62
    السكان
    -0.62
    jspx
    -0.60
    WithMany
    -0.56
     defaultstate
    -0.55
    出版年
    -0.53
    InjectAttribute
    -0.52
    ]--;
    -0.51
    ]++;
    -0.50
    POSITIVE LOGITS
     data
    0.84
     privacy
    0.83
     confidentiality
    0.81
     confidential
    0.77
     leakage
    0.73
     Data
    0.72
     gevo
    0.72
    Confidential
    0.72
     Privacy
    0.71
     HIPAA
    0.71
    Activations Density 0.202%

    No Known Activations