© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10123
    Prev
    Next
    INDEX
    Explanations

    contexts referring to wetness or dampness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "wet" or "wetting"

    np_acts-logits-general · gemini-2.0-flash

    wetness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſicht
    -0.82
     laſſen
    -0.82
    <unused3>
    -0.79
    <pad>
    -0.78
    <unused52>
    -0.78
    <unused17>
    -0.78
    <unused43>
    -0.78
    <unused42>
    -0.78
    <unused14>
    -0.78
    <unused16>
    -0.78
    POSITIVE LOGITS
     wet
    2.19
    wet
    1.95
     Wet
    1.92
    Wet
    1.90
     WET
    1.59
    WET
    1.48
     wetter
    1.37
     wetting
    1.25
    湿
    1.17
     moist
    1.14
    Activations Density 0.151%

    No Known Activations