© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5764
    Prev
    Next
    INDEX
    Explanations

    terms related to data protection and security measures

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

    information security and data protection concepts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    jspx
    -0.38
    build
    -0.38
    light
    -0.35
     Fix
    -0.34
     Fine
    -0.34
    stiff
    -0.33
    lif
    -0.33
    Fix
    -0.33
     sti
    -0.32
    upol
    -0.32
    POSITIVE LOGITS
     privacy
    0.77
     security
    0.71
     Privacy
    0.69
     PRIVACY
    0.68
    privacy
    0.68
    Privacy
    0.68
     confidentiality
    0.68
     referrerpolicy
    0.68
     SECURITY
    0.63
    Security
    0.60
    Activations Density 0.213%

    No Known Activations