Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1016
    Prev
    Next
    INDEX
    Explanations

    references to journeys or exploration

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

    journeys, expeditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.66
     estekak
    -0.61
    GEBURTSDATUM
    -0.58
     AspNetCore
    -0.56
    存于互联网档案馆
    -0.54
    ymce
    -0.54
    IntoConstraints
    -0.53
    AndEndTag
    -0.51
    SpringBootTest
    -0.49
     MutableLiveData
    -0.49
    POSITIVE LOGITS
     expedition
    0.91
     Expedition
    0.85
     expeditions
    0.77
     pilgrimage
    0.75
     pilgri
    0.73
    Exped
    0.73
    Expedition
    0.69
     Exped
    0.65
     journey
    0.62
     Pilgrim
    0.62
    Activations Density 0.010%

    No Known Activations