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. 13-GEMMASCOPE-RES-16K
    6. 16131
    Prev
    Next
    INDEX
    Explanations

    terms related to friendliness and positive social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endpush
    -0.87
    ⓧ
    -0.84
     uVar
    -0.74
    RegistryLite
    -0.74
    subplots
    -0.73
    UnsafeEnabled
    -0.69
     eventdata
    -0.69
     NSCoder
    -0.69
     IMDG
    -0.68
    /***/
    -0.67
    POSITIVE LOGITS
     friendly
    0.82
     welcoming
    0.78
     friendliness
    0.75
    Friendly
    0.74
     Friendly
    0.73
     gentler
    0.72
     welcome
    0.71
     vriende
    0.70
    friendly
    0.70
     gentle
    0.69
    Activations Density 0.159%

    No Known Activations