© 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. 58733
    Prev
    Next
    INDEX
    Explanations

    instances of the word "chosen" in various forms

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

    "chosen" followed by a noun

    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
     Wikiseite
    -0.58
    erover
    -0.53
    ytale
    -0.52
    orgue
    -0.50
     Antarctica
    -0.50
     ProductService
    -0.50
     Spitze
    -0.50
    BeanFactory
    -0.50
    ardis
    -0.49
     wikipagina
    -0.49
    POSITIVE LOGITS
     chosen
    1.98
    chosen
    1.92
    Chosen
    1.84
     Chosen
    1.79
     elegido
    1.10
     escolh
    1.10
     выбран
    0.97
     choisi
    0.96
     Choose
    0.92
     scelto
    0.92
    Activations Density 0.007%

    No Known Activations