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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 618
    Prev
    Next
    INDEX
    Explanations

    expressions related to reassurance and emotional well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ladders
    -0.40
     мәкал
    -0.40
    queryInterface
    -0.39
     IBOutlet
    -0.39
    Ifc
    -0.38
    PointerException
    -0.38
     Crimin
    -0.37
    cabulary
    -0.37
     Formats
    -0.37
     useAppContext
    -0.37
    POSITIVE LOGITS
    安心
    0.77
    安心して
    0.75
     安心
    0.66
     trust
    0.66
     reassured
    0.66
     confidence
    0.63
     confident
    0.63
     assured
    0.63
     assurance
    0.63
     relieved
    0.63
    Activations Density 0.173%

    No Known Activations