© 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. 20-GEMMASCOPE-RES-16K
    11. 3372
    Prev
    Next
    INDEX
    Explanations

    negative evaluations and expressions of disappointment or failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    negative outcomes

    np_acts-logits-general · gemini-2.0-flash

    failure, hurt, wrong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Παραπομπές
    -0.82
    IntoConstraints
    -0.81
     GenerationType
    -0.79
    tvguidetime
    -0.77
    GOTREF
    -0.77
    Geplaatst
    -0.71
     estekak
    -0.69
    //
    -0.64
    BeginContext
    -0.64
    Rptr
    -0.61
    POSITIVE LOGITS
     big
    1.01
     BIG
    0.95
     badly
    0.93
     dearly
    0.88
     migh
    0.87
    BIG
    0.87
     terribly
    0.85
    big
    0.84
     severely
    0.80
     sév
    0.79
    Activations Density 0.222%

    No Known Activations