© 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. 24-GEMMASCOPE-RES-16K
    11. 12291
    Prev
    Next
    INDEX
    Explanations

    terms related to safety and security issues

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

    Following "security"

    np_acts-logits-general · gemini-2.0-flash

    security applications and measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.77
    uxxxx
    -0.66
    Regular
    -0.50
    HasColumnName
    -0.49
    shire
    -0.48
    utriche
    -0.48
     Nef
    -0.47
    Denomin
    -0.47
     Yugos
    -0.46
    hips
    -0.46
    POSITIVE LOGITS
     Blanket
    0.68
     blanket
    0.66
     LoggerFactory
    0.65
    criture
    0.60
    ChildScrollView
    0.59
     guards
    0.58
    ContextHolder
    0.58
     clearance
    0.57
    astify
    0.56
     tightened
    0.54
    Activations Density 0.147%

    No Known Activations