© 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. 28-GEMMASCOPE-RES-16K
    11. 4166
    Prev
    Next
    INDEX
    Explanations

    instances of functions and their definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related text or documentation snippets

    np_acts-logits-general · gemini-2.0-flash

    ref-type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AlterField
    -0.46
     voetballer
    -0.39
     onCreateView
    -0.39
     Italijanski
    -0.39
    Enllaços
    -0.38
     außerdem
    -0.37
     Infatti
    -0.35
     Komunikasi
    -0.34
    >{@
    -0.34
     Voraus
    -0.34
    POSITIVE LOGITS
    IsContent
    0.75
     nakalista
    0.74
    AddTagHelper
    0.61
     EconPapers
    0.57
    Hochspringen
    0.54
     kasarigan
    0.50
    はじめに
    0.46
    lasma
    0.45
    MigrationBuilder
    0.44
    $__
    0.44
    Activations Density 0.074%

    No Known Activations