© 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. 9-GEMMASCOPE-RES-131K
    6. 125871
    Prev
    Next
    INDEX
    Explanations

    instances of the word "choices" in various contexts, emphasizing decision-making themes

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

    making choices

    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
     technically
    -0.60
     Technically
    -0.48
     network
    -0.47
    Technically
    -0.46
     aesthetically
    -0.46
     officially
    -0.45
     Mann
    -0.45
     rare
    -0.44
     nervous
    -0.44
     Originally
    -0.43
    POSITIVE LOGITS
     choices
    1.87
     Choices
    1.75
    Choices
    1.63
    choices
    1.58
    CHOICES
    1.16
     scelte
    1.03
     selections
    0.94
     decisions
    0.90
     options
    0.82
     Decisions
    0.82
    Activations Density 0.010%

    No Known Activations