© 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. 4-GEMMASCOPE-RES-16K
    11. 10454
    Prev
    Next
    INDEX
    Explanations

    references to support libraries in Android development

    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
     AssemblyCompany
    -0.58
    MessageState
    -0.56
     Jefus
    -0.55
     raiſ
    -0.53
    VersionUID
    -0.53
     Créez
    -0.52
     ſeveral
    -0.52
     fört
    -0.51
    otriz
    -0.50
     unſ
    -0.50
    POSITIVE LOGITS
    :][
    1.22
    ?[
    1.00
    GetMapping
    0.99
    @[+][
    0.93
     CreateTagHelper
    0.91
    Autowired
    0.85
    PathVariable
    0.76
    DockStyle
    0.74
     betweenstory
    0.74
    Varint
    0.72
    Activations Density 0.013%

    No Known Activations