© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7747
    Prev
    Next
    INDEX
    Explanations

    occurrences of the gerund form of verbs, particularly those ending in 'zing'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.84
    enderror
    -0.83
     iprot
    -0.81
    verwijspagina
    -0.79
    PageModule
    -0.77
    باردا
    -0.77
     tartalomajánló
    -0.76
     Rout
    -0.75
     surla
    -0.75
     Numerade
    -0.75
    POSITIVE LOGITS
     inwesty
    0.70
     inversión
    0.63
     investasi
    0.60
    investissement
    0.58
     investment
    0.58
     inwest
    0.57
     corporativa
    0.54
     invested
    0.52
     inversiones
    0.52
     investis
    0.49
    Activations Density 0.194%

    No Known Activations