© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 114683
    Prev
    Next
    INDEX
    Explanations

    sentences that contain general statements or observations about a subject

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

    in general,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.44
    DataSnapshot
    -0.43
     contamination
    -0.42
     addirittura
    -0.41
    まさかの
    -0.41
     Contamination
    -0.40
     organelles
    -0.40
     mitochondria
    -0.39
     mitochond
    -0.38
     convertirse
    -0.38
    POSITIVE LOGITS
     generally
    1.06
     Generally
    1.02
    Generally
    1.01
    generally
    0.95
     general
    0.81
     generell
    0.81
    一般
    0.81
    Typically
    0.80
     typically
    0.75
     Typically
    0.74
    Activations Density 0.039%

    No Known Activations