© 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. 17-GEMMASCOPE-RES-16K
    11. 716
    Prev
    Next
    INDEX
    Explanations

    expressions of care and concern for individuals or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.98
    complexContent
    -0.96
    BoxShadow
    -0.83
     nahilalakip
    -0.82
    enderror
    -0.81
    脚注の使い方
    -0.81
    HostException
    -0.81
    Portail
    -0.81
     GetEnumerator
    -0.78
    ELTS
    -0.78
    POSITIVE LOGITS
     Care
    0.98
     care
    0.95
     CARE
    0.92
    CARE
    0.92
    Care
    0.83
     caring
    0.72
    care
    0.72
     cared
    0.72
    ecare
    0.72
     cares
    0.71
    Activations Density 0.043%

    No Known Activations