© 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-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 7370
    Prev
    Next
    INDEX
    Explanations

    code snippets and tags related to programming languages, particularly HTML and PHP

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.84
    endphp
    -0.71
    AndEndTag
    -0.68
    TagMode
    -0.65
    +#+#
    -0.64
    MigrationBuilder
    -0.62
     pinulongan
    -0.59
     iprot
    -0.59
    AnchorStyles
    -0.59
    AccessorTable
    -0.57
    POSITIVE LOGITS
     tertentu
    0.51
    Související
    0.46
    stateProvider
    0.44
    specific
    0.42
     determinadas
    0.40
     specific
    0.39
     Hecht
    0.39
     bijzondere
    0.38
     McLaughlin
    0.38
     particular
    0.37
    Activations Density 0.088%

    No Known Activations