© 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. 9-GEMMASCOPE-RES-131K
    11. 99179
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "research" and its variations in different contexts

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

    research and scientific inquiry

    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
     duide
    -0.47
     ifølge
    -0.47
     Punkt
    -0.42
     ισ
    -0.42
     onderdelen
    -0.40
     effector
    -0.40
     portas
    -0.39
     Clough
    -0.39
     carotid
    -0.38
     goederen
    -0.38
    POSITIVE LOGITS
     research
    1.58
    research
    1.24
     researches
    1.13
     RESEARCH
    1.05
     investigación
    1.01
    RESEARCH
    0.99
     researching
    0.98
     ricerca
    0.94
     pesquisa
    0.92
     ricerche
    0.92
    Activations Density 0.019%

    No Known Activations