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. 75039
    Prev
    Next
    INDEX
    Explanations

    references to the concept of aging and its related terms

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

    aging alters things

    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
    verwijspagina
    -0.68
     indisponible
    -0.61
     للمعارف
    -0.61
    mybatisplus
    -0.60
    RenderAtEndOf
    -0.57
    RegistryLite
    -0.54
     مرئيه
    -0.52
     ब्रेकडाउन
    -0.52
    SPATH
    -0.52
     τὸ
    -0.50
    POSITIVE LOGITS
    Aging
    1.15
     aging
    1.05
     Aging
    1.02
     vieill
    0.98
     ageing
    0.96
     envejec
    0.92
    vejec
    0.84
     âgé
    0.69
    Aged
    0.67
    getAge
    0.67
    Activations Density 0.006%

    No Known Activations