© 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. 28-GEMMASCOPE-RES-16K
    11. 8038
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or situational contexts

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

    "at" followed by a time-related word

    np_acts-logits-general · gemini-2.0-flash

    at times, at night, at random

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.39
    complexContent
    -0.35
    पया
    -0.34
     venons
    -0.32
     Wirken
    -0.32
    ographia
    -0.30
     Weise
    -0.30
     electron
    -0.30
     Elektronik
    -0.29
    ismer
    -0.29
    POSITIVE LOGITS
    EndContext
    0.58
    Спасылкі
    0.53
    RegressionTest
    0.53
     betweenstory
    0.53
    TestingModule
    0.50
     esternos
    0.50
    makeConstraints
    0.49
    parsedMessage
    0.48
    ="@+
    0.48
    EndGlobal
    0.48
    Activations Density 0.170%

    No Known Activations