© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15556
    Prev
    Next
    INDEX
    Explanations

    phrases expressing sympathy and comfort

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

    following words of comfort or support

    np_acts-logits-general · gemini-2.0-flash

    providing comfort and reassurance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    воро
    -0.44
    dropIfExists
    -0.43
     bun
    -0.43
    ilí
    -0.42
    abstractmethod
    -0.42
    Groom
    -0.42
    getDrawable
    -0.42
    dit
    -0.41
     đào
    -0.41
    ximately
    -0.41
    POSITIVE LOGITS
     comfort
    1.84
     consolation
    1.74
     comforting
    1.71
     solace
    1.67
     comforted
    1.66
    comfort
    1.63
     relief
    1.53
     comforts
    1.52
     reassurance
    1.50
     Comfort
    1.46
    Activations Density 0.171%

    No Known Activations