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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75028
    Prev
    Next
    INDEX
    Explanations

    phrases related to gathering or bringing people together

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

    coming together or gathering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Paglinawan
    -0.59
     squeak
    -0.43
    XDECREF
    -0.43
    EndInit
    -0.42
    fahrens
    -0.41
     ddelweddau
    -0.40
    zeß
    -0.40
    Kjelder
    -0.40
     Shaksp
    -0.39
    quedas
    -0.39
    POSITIVE LOGITS
     gathering
    0.89
     gatherings
    0.87
     meeting
    0.84
     Meeting
    0.79
     Gathering
    0.78
    Gathering
    0.76
    gathering
    0.76
    Meeting
    0.76
     riun
    0.74
     meetings
    0.74
    Activations Density 0.013%

    No Known Activations