Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11316
    Prev
    Next
    INDEX
    Explanations

    financial terms related to investments and acquisitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.48
     simplifié
    -0.45
     NavController
    -0.43
     zoude
    -0.42
    msgTypes
    -0.42
    contentLoaded
    -0.42
    SourceChecksum
    -0.40
    MemoryWarning
    -0.40
    aarrggbb
    -0.40
    InjectAttribute
    -0.40
    POSITIVE LOGITS
     onOptions
    0.47
     (<
    0.46
     antal
    0.43
     élevée
    0.40
     élevé
    0.40
     porcentaje
    0.40
    verwijspagina
    0.39
     (.
    0.38
     gla
    0.38
     (~
    0.37
    Activations Density 1.227%

    No Known Activations