© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12686
    Prev
    Next
    INDEX
    Explanations

    terminology related to persistence or prolonged existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iprot
    -0.49
     Chriftian
    -0.46
     Eſ
    -0.46
     bucal
    -0.43
    flashdata
    -0.42
     cerim
    -0.40
    Endian
    -0.40
     Schluß
    -0.40
     Christiansen
    -0.39
    ntesis
    -0.39
    POSITIVE LOGITS
     persist
    0.90
     persists
    0.88
     persistence
    0.81
    persist
    0.79
     persisted
    0.79
     Persistent
    0.78
     persistent
    0.77
     Persistence
    0.75
     jest
    0.73
    persistent
    0.66
    Activations Density 0.151%

    No Known Activations