© 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. 0-GEMMASCOPE-RES-16K
    11. 7861
    Prev
    Next
    INDEX
    Explanations

    phrases related to care, particularly in a caregiving or health context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.88
     auffi
    -0.88
     themſelves
    -0.88
     Monfieur
    -0.87
    ConstraintMaker
    -0.81
     ſeveral
    -0.80
     himſelf
    -0.79
     pleaſure
    -0.79
     ſhe
    -0.79
     Brescia
    -0.79
    POSITIVE LOGITS
     call
    0.63
     app
    0.58
     Made
    0.58
     I
    0.53
    Glad
    0.51
    care
    0.49
    hat
    0.49
     Glad
    0.46
    I
    0.46
     care
    0.45
    Activations Density 0.227%

    No Known Activations