© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4215
    Prev
    Next
    INDEX
    Explanations

    mentions of privacy-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    weight
    -0.53
     CreateTagHelper
    -0.51
    Weight
    -0.51
     Brecht
    -0.51
     الط
    -0.48
    omalainen
    -0.47
     ATH
    -0.46
    ParallelGroup
    -0.46
    clusal
    -0.46
     mode
    -0.46
    POSITIVE LOGITS
     privacy
    0.96
     Privacy
    0.93
    PRIVACY
    0.91
    Privacy
    0.90
    privacy
    0.89
    Cyber
    0.88
     PRIVACY
    0.86
    Hochspringen
    0.85
    cyber
    0.84
     cyber
    0.84
    Activations Density 0.055%

    No Known Activations