© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 3589
    Prev
    Next
    INDEX
    Explanations

    phrases related to hanging or being suspended

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otas
    -0.47
    SELECTED
    -0.45
    ľad
    -0.44
     Gesch
    -0.44
    Heinz
    -0.42
    藩
    -0.41
    tiera
    -0.40
     pisos
    -0.40
    REFERRED
    -0.40
     Fox
    -0.40
    POSITIVE LOGITS
     HANG
    1.52
     Hang
    1.51
     hang
    1.51
     hung
    1.39
     hanging
    1.35
     hangs
    1.35
     Hanging
    1.33
    Hanging
    1.32
    Hang
    1.31
    hanging
    1.25
    Activations Density 0.068%

    No Known Activations