© 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. 20893
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Phoenix" and variations of "phenol" and "phenolic"

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

    Phoenix, phenol, phen-

    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
    import
    -0.56
    divarius
    -0.50
     consultato
    -0.48
    outState
    -0.48
     jScrollPane
    -0.45
     Magi
    -0.45
    rzost
    -0.44
    IMPORTED
    -0.44
    artes
    -0.43
     dsg
    -0.42
    POSITIVE LOGITS
     Phoenix
    0.90
    Phoenix
    0.88
     Phen
    0.82
    phoenix
    0.79
     phoenix
    0.78
    ENIX
    0.75
    Phen
    0.72
     phen
    0.70
     OnInit
    0.69
     Phe
    0.66
    Activations Density 0.019%

    No Known Activations