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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3331
    Prev
    Next
    INDEX
    Explanations

    expressions related to caregiving and responsibility

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

    expressions about providing care or taking care of someone or something.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.50
     فريبيس
    -0.48
     useRouter
    -0.46
     MaterialApp
    -0.44
     estekak
    -0.43
     ligiloj
    -0.42
    IntoConstraints
    -0.42
    StoryboardSegue
    -0.40
    ņš
    -0.40
    RTDA
    -0.39
    POSITIVE LOGITS
     care
    2.30
     cared
    1.88
    care
    1.88
     caring
    1.75
     Care
    1.73
     cuidados
    1.68
     cuidado
    1.66
    Care
    1.64
     cuidar
    1.60
    Caring
    1.59
    Activations Density 0.327%

    No Known Activations