© 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. 31220
    Prev
    Next
    INDEX
    Explanations

    references to the term "PINK" and its variants in various contexts

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

    PINK1 and Pink Floyd

    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
    URLException
    -0.48
     Josiah
    -0.46
    horesis
    -0.43
     gewe
    -0.41
    SOA
    -0.40
    úly
    -0.40
     Groves
    -0.40
    izoen
    -0.39
     samh
    -0.39
     Whelan
    -0.39
    POSITIVE LOGITS
     Pink
    2.13
    Pink
    2.09
    PINK
    1.76
     PINK
    1.72
    pink
    1.62
     pink
    1.40
     pinky
    1.14
    ピンク
    0.94
     розовый
    0.90
     pinkish
    0.87
    Activations Density 0.011%

    No Known Activations