© 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. 20-GEMMASCOPE-RES-16K
    11. 2205
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to medical conditions and assessments of risks

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

    something is small or unimportant

    np_acts-logits-general · gemini-2.0-flash

    low severity or impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    dientemente
    -0.55
    mybatisplus
    -0.52
    urlpatterns
    -0.52
    iestety
    -0.51
    endphp
    -0.51
     violated
    -0.48
     unavailable
    -0.48
    horst
    -0.46
    المناصب
    -0.45
    toThrow
    -0.44
    POSITIVE LOGITS
     harmless
    1.38
     mild
    1.24
     minor
    1.16
     benign
    1.15
     insignificant
    1.14
     negligible
    1.11
     manageable
    1.08
     milder
    1.05
     innoc
    1.03
    mild
    1.02
    Activations Density 0.945%

    No Known Activations