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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 15738
    Prev
    Next
    INDEX
    Explanations

    references to the therapeutic benefits and healing properties of crochet

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

    Therapy, comfort, and healing

    np_acts-logits-general · gemini-2.0-flash

    calming therapeutic activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ыгана
    -0.71
     Савезне
    -0.68
    UserScript
    -0.67
     beginnetje
    -0.66
    qrstuvwxyz
    -0.66
    ⓘ
    -0.64
     Signalez
    -0.61
    ثيق
    -0.60
     المعيارى
    -0.60
    glades
    -0.59
    POSITIVE LOGITS
     therapy
    0.95
     soothing
    0.86
     Therapy
    0.85
     therapeutic
    0.83
     calming
    0.78
     THERAPY
    0.77
    therapy
    0.76
     therap
    0.75
     solace
    0.72
    Therapy
    0.70
    Activations Density 0.222%

    No Known Activations