© 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. 9-GEMMASCOPE-RES-16K
    6. 9267
    Prev
    Next
    INDEX
    Explanations

    references to technology, products, and services related to automotive design

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

    brand names and product/business identifiers that include combinations of letters and numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Халык
    -0.53
    kesha
    -0.50
     المعيارى
    -0.49
    Majestic
    -0.49
    şört
    -0.48
     Regal
    -0.47
    RegressionTest
    -0.46
    ocratic
    -0.46
    ItemBackground
    -0.45
    othelioma
    -0.45
    POSITIVE LOGITS
    Declarations
    0.38
     rocha
    0.37
     rios
    0.36
     caras
    0.35
     Project
    0.35
     décal
    0.35
     collectif
    0.34
    contentPane
    0.34
     prefi
    0.34
     doInBackground
    0.34
    Activations Density 0.696%

    No Known Activations