© 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. 3-GEMMASCOPE-RES-16K
    11. 7885
    Prev
    Next
    INDEX
    Explanations

    terms related to defense and protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LLocation
    -0.78
    +:+
    -0.72
    ,:);
    -0.71
    ]")]
    -0.69
     CascadeType
    -0.69
     CreateTagHelper
    -0.68
     المعيارى
    -0.67
     ویکی‌پدیای
    -0.65
    amaño
    -0.59
     NSCoder
    -0.59
    POSITIVE LOGITS
     defend
    2.02
     defends
    1.85
     defended
    1.82
     defending
    1.81
     Defend
    1.80
     defense
    1.69
     defence
    1.66
     protect
    1.53
    defense
    1.52
    defence
    1.51
    Activations Density 0.316%

    No Known Activations