© 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. 20-GEMMASCOPE-RES-131K
    6. 57863
    Prev
    Next
    INDEX
    Explanations

    references to engineering and engineers

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

    engineering contexts

    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
    thenReturn
    -0.49
    Diario
    -0.40
     passend
    -0.40
     Baran
    -0.39
    rrggbb
    -0.39
     happiest
    -0.38
     appunto
    -0.38
    makeText
    -0.38
    masin
    -0.37
    Captor
    -0.37
    POSITIVE LOGITS
     engineering
    1.30
    engineering
    1.18
     Engineering
    1.18
    Engineering
    1.09
     ENGINEERING
    1.01
     engineer
    0.98
     engineers
    0.94
    engineer
    0.94
     Engineer
    0.92
     Engineers
    0.92
    Activations Density 0.007%

    No Known Activations