© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 97328
    Prev
    Next
    INDEX
    Explanations

    references to moisture

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

    moisture presence and humidity

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Autoritní
    -0.53
    bootstrapcdn
    -0.52
    îné
    -0.51
    FlatAppearance
    -0.49
    Ld
    -0.47
    oredCriteria
    -0.47
     arrayOf
    -0.47
    Called
    -0.47
    IFORN
    -0.47
     Aleks
    -0.46
    POSITIVE LOGITS
     moisture
    1.84
     Moisture
    1.75
    Moisture
    1.66
    moisture
    1.55
     humedad
    1.13
     Feuchtigkeit
    0.95
    humidité
    0.87
     moist
    0.86
    水分
    0.84
     Moist
    0.75
    Activations Density 0.004%

    No Known Activations