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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15564
    Prev
    Next
    INDEX
    Explanations

    beginning or section markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    SequentialGroup
    -1.11
     defaultstate
    -0.77
    AndroidJUnit
    -0.73
    ChildScrollView
    -0.73
    complexContent
    -0.72
    addCriterion
    -0.72
    OfWork
    -0.71
    énario
    -0.70
    XmlRootElement
    -0.68
     RequestMethod
    -0.65
    POSITIVE LOGITS
    RegressionTest
    0.62
     Jefus
    0.57
     occhiali
    0.55
     attiv
    0.54
     themſelves
    0.54
     tiegħek
    0.52
     ſhall
    0.51
     saluti
    0.51
     becauſe
    0.51
     himſelf
    0.51
    Activations Density 0.065%

    No Known Activations