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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113936
    Prev
    Next
    INDEX
    Explanations

    concepts and words related to unity and togetherness

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

    unity

    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
     onPage
    -0.48
    StatusBadRequest
    -0.46
    AddWithValue
    -0.46
     Malfoy
    -0.44
    apeno
    -0.44
     exorbit
    -0.43
    ◗
    -0.43
    WireFormatLite
    -0.41
    ScrollBar
    -0.41
    cookieParser
    -0.40
    POSITIVE LOGITS
     unity
    1.07
     uniting
    1.02
     Unity
    0.97
     unite
    0.97
     Unite
    0.94
     unites
    0.92
     united
    0.90
     unify
    0.90
    unity
    0.89
     unified
    0.88
    Activations Density 0.017%

    No Known Activations