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. 14065
    Prev
    Next
    INDEX
    Explanations

    personal relationships and significant life events

    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
    RectangleBorder
    -0.48
     når
    -0.47
    Personendaten
    -0.46
     AsyncTask
    -0.46
    DebuggerNonUser
    -0.45
    Occasionally
    -0.43
    setOnItem
    -0.43
    exitRule
    -0.42
    setupUi
    -0.42
     sometimes
    -0.41
    POSITIVE LOGITS
     thereafter
    2.00
     subsequently
    1.92
     subsequent
    1.86
     Subsequently
    1.81
     Thereafter
    1.76
     Subsequent
    1.75
     afterwards
    1.53
    その後
    1.51
     afterward
    1.47
    óta
    1.45
    Activations Density 0.589%

    No Known Activations