© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3675
    Prev
    Next
    INDEX
    Explanations

    references to cache management and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.47
    styleType
    -0.43
    interopRequire
    -0.43
    EndProject
    -0.40
    :✨
    -0.40
     lenker
    -0.39
    AutoresizingMask
    -0.39
    intios
    -0.37
    يميديا
    -0.37
     ruban
    -0.36
    POSITIVE LOGITS
     cache
    2.88
     Cache
    2.63
    cache
    2.48
    Cache
    2.38
     caches
    2.30
     CACHE
    2.25
     caching
    2.13
    CACHE
    2.06
     cached
    2.02
    缓存
    1.92
    Activations Density 0.651%

    No Known Activations