© 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. 40-GEMMASCOPE-RES-16K
    6. 2308
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to isolation and data collection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.46
     dAtA
    -0.40
    Suara
    -0.37
    র
    -0.37
     estekak
    -0.36
     ***!
    -0.35
     NUKAT
    -0.35
     esternos
    -0.34
    Persist
    -0.34
     utafitiHapana
    -0.33
    POSITIVE LOGITS
     successful
    0.68
     arsenic
    0.64
     oregon
    0.62
     preco
    0.58
     erst
    0.57
     caller
    0.56
     enactment
    0.56
     connected
    0.55
     nationalist
    0.54
     truthful
    0.54
    Activations Density 0.132%

    No Known Activations