Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2834
    Prev
    Next
    INDEX
    Explanations

    contexts related to the concept of care and caregiving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.18
     فريبيس
    -1.10
    IsMutable
    -1.08
    MigrationBuilder
    -1.08
     للمعارف
    -1.05
    principalColumn
    -1.05
    HostException
    -1.04
    complexContent
    -1.02
    parsedMessage
    -0.99
     ExecuteAsync
    -0.99
    POSITIVE LOGITS
    taking
    0.58
    takers
    0.56
    giving
    0.53
    CARE
    0.52
     cared
    0.50
     zorg
    0.50
     Care
    0.49
     care
    0.49
    sses
    0.48
    ful
    0.47
    Activations Density 0.116%

    No Known Activations