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. 9-GEMMASCOPE-RES-131K
    6. 81429
    Prev
    Next
    INDEX
    Explanations

    variations of the word "being" and its usage in different contexts

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

    state or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.54
     lenker
    -0.54
    فایل‌لار
    -0.48
     vė
    -0.48
    expandindo
    -0.44
    둑
    -0.44
     Wikimedijinoj
    -0.43
     szczeg
    -0.43
     Schlä
    -0.42
    BibitemShut
    -0.42
    POSITIVE LOGITS
    Being
    1.18
     Being
    1.08
     BEING
    0.91
    being
    0.87
     being
    0.70
    Knowing
    0.60
     Knowing
    0.54
    Having
    0.54
     estando
    0.53
     knowing
    0.50
    Activations Density 0.013%

    No Known Activations