© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 107434
    Prev
    Next
    INDEX
    Explanations

    instances of the word "persist" and its variations indicating ongoing actions or states

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

    continues to exist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Moulton
    -0.57
     clor
    -0.56
     McDonnell
    -0.50
    bonucleic
    -0.48
    nail
    -0.47
    Shoes
    -0.47
     Administrativna
    -0.46
     gine
    -0.46
     cag
    -0.46
     Sociological
    -0.46
    POSITIVE LOGITS
     persists
    1.94
     persist
    1.84
     persisted
    1.68
     persiste
    1.37
    persist
    1.27
     persistence
    1.20
    Persist
    1.07
     Persistence
    1.05
     persevere
    0.98
    persistence
    0.93
    Activations Density 0.008%

    No Known Activations