© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 6806
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate roles or identities in a contextual framework

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

    Followed by certain prepositions or parentheses

    np_acts-logits-general · gemini-2.0-flash

    introducing specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    parsedMessage
    -0.56
    +:+
    -0.55
    出版年
    -0.49
     propOrder
    -0.48
     encontrarse
    -0.47
    RegressionTest
    -0.42
     intégral
    -0.41
    arXiv
    -0.40
     recevrez
    -0.40
    élica
    -0.40
    POSITIVE LOGITS
     MaterialApp
    0.41
     stockholders
    0.40
     AssemblyProduct
    0.40
    AddWithValue
    0.39
     коллек
    0.38
     designers
    0.38
    developers
    0.38
     growers
    0.37
     shareholders
    0.37
     Rumuni
    0.37
    Activations Density 0.096%

    No Known Activations