© 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. 9223
    Prev
    Next
    INDEX
    Explanations

    terms related to drying and preparation processes in scientific contexts

    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
    rungsseite
    -0.53
     AssemblyVersion
    -0.45
    Panamoan
    -0.42
    ItemBackground
    -0.41
    AppMethodBeat
    -0.40
    URLException
    -0.36
    webElementGuid
    -0.36
    GEBURTSDATUM
    -0.35
    Personensuche
    -0.35
    ⟬
    -0.35
    POSITIVE LOGITS
     dry
    3.42
    dry
    2.94
    Dry
    2.89
     Dry
    2.89
     drying
    2.78
     dried
    2.70
     dries
    2.66
     DRY
    2.63
     dryness
    2.61
    DRY
    2.44
    Activations Density 0.594%

    No Known Activations