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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7134
    Prev
    Next
    INDEX
    Explanations

    references to Java programming language components and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.39
    HtmlAttribute
    -1.37
    ContentAsync
    -0.97
    Hozzáférés
    -0.96
     propOrder
    -0.90
     CreateTagHelper
    -0.89
    setVerticalGroup
    -0.86
     שוליים
    -0.84
    AccessorTable
    -0.83
    SourceChecksum
    -0.82
    POSITIVE LOGITS
    ComponentModel
    1.43
    awt
    0.99
     useEffect
    0.96
    useEffect
    0.84
     useState
    0.76
    useState
    0.74
     OnInit
    0.63
    stdlib
    0.61
    stereotype
    0.60
    ard
    0.57
    Activations Density 0.011%

    No Known Activations