© 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. 38-GEMMASCOPE-RES-16K
    6. 13208
    Prev
    Next
    INDEX
    Explanations

    details about kitchen appliances and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.49
     nawr
    -0.49
    ngdoc
    -0.46
     plates
    -0.45
     gasket
    -0.43
     gaskets
    -0.42
     Tiles
    -0.42
     Plates
    -0.41
     Platten
    -0.41
     Strain
    -0.40
    POSITIVE LOGITS
     stick
    1.32
     rod
    1.27
     sticks
    1.21
     rods
    1.17
    stick
    1.09
     Stick
    1.05
    sticks
    0.99
    Stick
    0.98
     pole
    0.97
     shaft
    0.97
    Activations Density 0.879%

    No Known Activations