© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 703
    Prev
    Next
    INDEX
    Explanations

    references to the term "ph" indicating a connection to pharmaceuticals or related topics

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

    references to the abbreviation "Ph" or related terms

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

    words starting with ph

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    EndContext
    -0.88
     InputDecoration
    -0.87
     Theſe
    -0.85
     faſt
    -0.84
     themſelves
    -0.83
     itſelf
    -0.82
     myſelf
    -0.82
     ſeveral
    -0.81
     Monfieur
    -0.79
     bershka
    -0.75
    POSITIVE LOGITS
     Ph
    0.91
     ph
    0.84
    Ph
    0.81
    ph
    0.73
    phar
    0.56
    oph
    0.55
    PH
    0.50
    ENIX
    0.50
     PH
    0.48
    Phas
    0.48
    Activations Density 0.033%

    No Known Activations