© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4635
    Prev
    Next
    INDEX
    Explanations

    situations and expressions related to "falling" and "failure."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیکھیے
    -0.69
    ushima
    -0.50
    Luong
    -0.48
    CLE
    -0.47
    väll
    -0.47
     Dinamarca
    -0.47
     betrug
    -0.47
    駿
    -0.47
    ↵↵↵↵
    -0.46
     Rad
    -0.46
    POSITIVE LOGITS
    FALL
    1.45
     FALL
    1.42
    falls
    1.40
    fall
    1.39
     falls
    1.34
    falling
    1.32
     fall
    1.30
    Fall
    1.29
     fell
    1.28
    Falls
    1.27
    Activations Density 0.073%

    No Known Activations