© 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. 11868
    Prev
    Next
    INDEX
    Explanations

    references to accountability and responsibility in customer service interactions

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

    Expressions of care, respect, or value

    np_acts-logits-general · gemini-2.0-flash

    expressions of genuine care

    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
    InjectAttribute
    -0.66
    Билгалдахарш
    -0.58
    oredCriteria
    -0.54
    المناصب
    -0.53
     useHistory
    -0.50
    UnusedPrivate
    -0.49
    MockMvc
    -0.47
    expandindo
    -0.47
    TestingModule
    -0.46
    تقاوى
    -0.46
    POSITIVE LOGITS
     cares
    1.40
     genuinely
    1.14
     cared
    1.10
     sincere
    1.10
     sincerely
    1.09
     caring
    1.07
    genu
    1.06
     care
    1.02
     Cares
    1.02
     sincerity
    1.02
    Activations Density 0.286%

    No Known Activations