© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4939
    Prev
    Next
    INDEX
    Explanations

    expressions of regret or disappointment about past decisions

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

    Expressions of regret or remorse

    np_acts-logits-general · gemini-2.0-flash

    regret, mistakes, gladness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToMap
    -0.37
     Официальный
    -0.35
     sphere
    -0.28
     DEM
    -0.26
     legis
    -0.26
    contentLoaded
    -0.25
    ophobia
    -0.25
    gefahr
    -0.24
    Feature
    -0.24
    Callback
    -0.24
    POSITIVE LOGITS
    SourceChecksum
    0.68
    ArgsConstructor
    0.67
     regretted
    0.65
     regrets
    0.65
     незавершена
    0.64
     hindsight
    0.64
    EndContext
    0.64
     utafitiHapana
    0.63
     محفوظة
    0.63
    當初
    0.63
    Activations Density 0.177%

    No Known Activations