© 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. 20-GEMMASCOPE-RES-131K
    6. 20510
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thoughts" and related terms that express ideas or beliefs

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

    thoughts

    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
    EndInit
    -0.63
     <>",
    -0.60
    <bos>
    -0.57
    mobileqq
    -0.56
     endIndex
    -0.56
    yelitis
    -0.55
     barons
    -0.52
     jspb
    -0.52
     exporters
    -0.50
     Kade
    -0.49
    POSITIVE LOGITS
     thoughts
    1.02
     Thoughts
    1.01
    Thoughts
    0.98
    thoughts
    0.97
    thought
    0.93
    Thought
    0.91
     THOUGHTS
    0.90
     Thought
    0.86
     thought
    0.85
     THOUGHT
    0.83
    Activations Density 0.007%

    No Known Activations