© 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 - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 490
    Prev
    Next
    INDEX
    Explanations

    technical jargon and structured elements related to programming or coding

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

    markdown section references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    magitan
    -0.32
    AtIndexPath
    -0.32
    ItemSelected
    -0.30
    PhysRevD
    -0.30
     Polsek
    -0.29
     mesure
    -0.29
     automatiques
    -0.27
     Wiel
    -0.27
     AssemblyTitle
    -0.27
     Polres
    -0.27
    POSITIVE LOGITS
     surla
    0.75
     nahilalakip
    0.67
    verifyException
    0.66
    WriteBarrier
    0.63
    Tikang
    0.62
    JAKARTA
    0.60
    出版年
    0.57
    RegressionTest
    0.56
    ]=>
    0.55
     droppings
    0.55
    Activations Density 0.218%

    No Known Activations