© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 37693
    Prev
    Next
    INDEX
    Explanations

    terms related to passive and active classifications, particularly in the context of immunizations and solar energy

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

    passive states and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.76
    rungsseite
    -0.70
     ویکی‌پدی
    -0.66
    fjspx
    -0.63
    AddTagHelper
    -0.59
     autorytatywna
    -0.59
     MainAxisSize
    -0.59
     Administrativna
    -0.57
    rawDesc
    -0.57
     getItemId
    -0.56
    POSITIVE LOGITS
     Passive
    0.83
    Passive
    0.80
     passive
    0.80
    passive
    0.71
     passively
    0.67
    被动
    0.56
     passi
    0.55
    Inactive
    0.54
     inactive
    0.50
     Pas
    0.50
    Activations Density 0.014%

    No Known Activations