© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3526
    Prev
    Next
    INDEX
    Explanations

    references to wetness or moisture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.67
     Lampung
    -0.67
    XmlType
    -0.67
     tangerang
    -0.65
    المراجع
    -0.64
    ModelSerializer
    -0.61
     Schild
    -0.59
    ạch
    -0.59
    inement
    -0.58
    HandlerContext
    -0.58
    POSITIVE LOGITS
     wet
    4.78
     Wet
    4.10
    wet
    4.05
    Wet
    3.98
     WET
    3.30
    WET
    2.89
     wetter
    2.44
     wetting
    2.35
     moist
    2.18
     basah
    1.99
    Activations Density 0.053%

    No Known Activations