© 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. 39-GEMMASCOPE-RES-16K
    6. 1071
    Prev
    Next
    INDEX
    Explanations

    references to complex organizational structures or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WITHOUT
    -0.48
     WITHOUT
    -0.48
    Rüyada
    -0.46
     without
    -0.42
     دون
    -0.40
    دانشنامهٔ
    -0.40
    expandindo
    -0.40
    ()==
    -0.39
    但不
    -0.38
     Unfortunately
    -0.36
    POSITIVE LOGITS
     nor
    3.80
    nor
    2.94
     Nor
    2.86
    Nor
    2.78
     NOR
    2.13
     Tampoco
    2.13
     tampoco
    2.03
     neither
    1.99
    NOR
    1.97
    而是
    1.78
    Activations Density 0.930%

    No Known Activations