© 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. 33-GEMMASCOPE-RES-16K
    11. 424
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "fall" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geſ
    -0.43
    ✢
    -0.42
    makeText
    -0.40
     Anſ
    -0.40
    合わせ
    -0.39
     ſont
    -0.39
    eradish
    -0.39
    dialect
    -0.39
     beverly
    -0.39
     preſent
    -0.39
    POSITIVE LOGITS
     fell
    1.02
     falling
    0.99
     fall
    0.93
    fell
    0.88
     FALL
    0.88
     falls
    0.87
     Falling
    0.86
    falling
    0.85
    Falling
    0.83
    falls
    0.82
    Activations Density 0.075%

    No Known Activations