© 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. 11-GEMMASCOPE-RES-16K
    11. 14441
    Prev
    Next
    INDEX
    Explanations

    phrases related to trouble or difficulties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thentic
    -0.69
    psack
    -0.66
    gasus
    -0.65
    riors
    -0.65
    |||
    -0.63
    ResponseWriter
    -0.63
    ppert
    -0.61
     KONG
    -0.61
    amkeit
    -0.61
     Levi
    -0.61
    POSITIVE LOGITS
     trouble
    1.19
     Trouble
    1.16
    trouble
    1.09
    Trouble
    1.02
     }}"></
    1.01
     troubles
    0.93
     Troubles
    0.86
     pleaſure
    0.84
    UBLE
    0.80
     NUKAT
    0.79
    Activations Density 0.082%

    No Known Activations