© 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. 2-GEMMASCOPE-RES-16K
    6. 4549
    Prev
    Next
    INDEX
    Explanations

    specific temporal references such as days and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.53
    MLLoader
    -0.51
    الحياه
    -0.51
     Taktlose
    -0.51
    saraba
    -0.51
     doInBackground
    -0.50
    ParallelGroup
    -0.50
     betrekking
    -0.50
    parsedMessage
    -0.49
     pewno
    -0.49
    POSITIVE LOGITS
    EReference
    0.47
     AssemblyTitle
    0.42
    Ɓ
    0.36
    Obituary
    0.35
     Huber
    0.35
     autorytatywna
    0.35
     كورة
    0.35
     vertically
    0.35
     nobili
    0.34
    amilya
    0.34
    Activations Density 0.310%

    No Known Activations