© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10613
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "cache" and its related functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    
    -0.85
    GEBURTSDATUM
    -0.85
    CodedInputStream
    -0.81
    GenerationType
    -0.80
    gonic
    -0.80
     smtplib
    -0.79
     createSprite
    -0.76
    parsedMessage
    -0.76
    MigrationBuilder
    -0.75
    IndentedString
    -0.75
    POSITIVE LOGITS
    cache
    2.88
     cache
    2.88
     Cache
    2.73
    Cache
    2.70
    CACHE
    2.45
     CACHE
    2.36
     caches
    2.24
    getCache
    1.99
     caching
    1.98
     cached
    1.88
    Activations Density 0.022%

    No Known Activations