© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 14958
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to caregiving and personal support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DidLoad
    -0.57
    jad
    -0.56
    ‌
    -0.54
    гран
    -0.52
     suci
    -0.50
    abolic
    -0.50
    prs
    -0.49
    сь
    -0.49
    anti
    -0.48
    грани
    -0.48
    POSITIVE LOGITS
     care
    1.30
     cuida
    1.24
     soin
    1.19
     cared
    1.11
     soins
    1.07
     Care
    1.07
     cares
    1.07
     caring
    1.06
     cuid
    1.06
     CARE
    1.03
    Activations Density 0.084%

    No Known Activations