© 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. 2-GEMMASCOPE-RES-16K
    11. 4860
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness and gratitude, particularly related to surveys and celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.89
    VersionUID
    -0.81
    tagHelperRunner
    -0.81
    Personendaten
    -0.69
    AndroidJUnit
    -0.67
    selves
    -0.67
    kheim
    -0.66
    NameInMap
    -0.65
    EMPL
    -0.62
    knapp
    -0.61
    POSITIVE LOGITS
     fancy
    0.87
     Fancy
    0.77
    Fancy
    0.70
     comedy
    0.68
    Happy
    0.68
     Happy
    0.68
     Awards
    0.67
    awards
    0.65
    HAPPY
    0.64
     legislative
    0.63
    Activations Density 0.114%

    No Known Activations