© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7325
    Prev
    Next
    INDEX
    Explanations

    terms related to cache control and memory management

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

    Cache-related terms and code

    np_acts-logits-general · gemini-2.0-flash

    computer cache policies and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.72
    MigrationBuilder
    -0.70
    GEBURTSDATUM
    -0.69
     onOptions
    -0.67
    ArgsConstructor
    -0.65
    IndentedString
    -0.64
    цездатний
    -0.64
    LookAnd
    -0.64
    queryInterface
    -0.64
     BorderSide
    -0.64
    POSITIVE LOGITS
     cache
    2.80
     Cache
    2.59
    cache
    2.49
    Cache
    2.43
     CACHE
    2.24
     cached
    2.17
     caches
    2.15
     caching
    2.10
    CACHE
    2.09
    缓存
    1.84
    Activations Density 0.278%

    No Known Activations