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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 7691
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fall" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RadioGroup
    -0.83
     دیکھیے
    -0.71
     команди
    -0.70
    ürger
    -0.66
    cheme
    -0.66
     Robson
    -0.65
    ynth
    -0.65
    MemoryWarning
    -0.64
    userDetails
    -0.64
     أنّ
    -0.63
    POSITIVE LOGITS
     fall
    2.17
    FALL
    2.17
    fall
    2.15
     FALL
    2.10
    Fall
    2.02
     falls
    2.00
     Fall
    2.00
    falls
    1.87
    falling
    1.85
    Falls
    1.81
    Activations Density 0.023%

    No Known Activations