© 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. 15856
    Prev
    Next
    INDEX
    Explanations

    phrases related to concealment and hidden items

    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
     AssemblyCompany
    -0.46
     femininas
    -0.42
    LayoutStyle
    -0.42
     aufges
    -0.40
    programmer
    -0.40
     przechowy
    -0.40
     diser
    -0.38
    protoimpl
    -0.38
     Meksiku
    -0.37
    getragen
    -0.37
    POSITIVE LOGITS
     inside
    0.85
     atop
    0.85
     securely
    0.84
     underneath
    0.74
     next
    0.71
     neatly
    0.70
     somewhere
    0.68
    inside
    0.68
     upside
    0.66
     beneath
    0.66
    Activations Density 0.659%

    No Known Activations