© 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. 20-GEMMASCOPE-RES-16K
    11. 1486
    Prev
    Next
    INDEX
    Explanations

    function calls related to resource management and cleanup in programming

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

    programming language operations like close(), free(), etc.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleable
    -0.78
    AddTagHelper
    -0.63
    bootstrapcdn
    -0.59
     queſta
    -0.57
     nonUne
    -0.57
    transQ
    -0.54
    tagHelperRunner
    -0.53
    writeField
    -0.52
     $_(
    -0.52
     вікісторінку
    -0.50
    POSITIVE LOGITS
    EndContext
    0.85
    principalTable
    0.57
    UseVisualStyle
    0.41
    GOTREF
    0.39
     aguja
    0.35
     lecteur
    0.34
     iNdEx
    0.33
     oprot
    0.33
     afterwards
    0.32
    نامه
    0.32
    Activations Density 0.120%

    No Known Activations