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. 20-GEMMASCOPE-RES-16K
    6. 14226
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.58
    lwjgl
    -0.53
     propOrder
    -0.52
     ujednoznacz
    -0.48
     resourceCulture
    -0.46
     vœux
    -0.45
     AppCompat
    -0.44
    ⇑
    -0.44
    borderBottom
    -0.44
    éfonos
    -0.43
    POSITIVE LOGITS
     ask
    0.85
     asked
    0.83
     asks
    0.83
    StructEnd
    0.82
     asking
    0.80
    来找
    0.76
     invited
    0.75
     reciproc
    0.73
     Asking
    0.72
     invitation
    0.71
    Activations Density 0.505%

    No Known Activations