© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11672
    Prev
    Next
    INDEX
    Explanations

    numerical and dimensional data, particularly involving measurements and identifiers

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

    numerical patterns in structured data or code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Vidite
    -0.75
    IUrlHelper
    -0.73
     Италијани
    -0.71
     kaarangay
    -0.71
    GTCX
    -0.60
    Clik
    -0.60
    +#+
    -0.57
     Biôgrafia
    -0.56
    хьтан
    -0.55
    transQ
    -0.55
    POSITIVE LOGITS
     soggior
    0.41
     jäsen
    0.40
    hdashline
    0.39
    viamo
    0.36
     satunya
    0.36
     pinggang
    0.34
     candidatos
    0.34
     "..\..\..\
    0.34
    Семья
    0.33
     createState
    0.33
    Activations Density 0.658%

    No Known Activations