© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10572
    Prev
    Next
    INDEX
    Explanations

    expressions of disappointment and emotional reactions

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

    associated with sadness or disappointment

    np_acts-logits-general · gemini-2.0-flash

    sad disappointment regret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.56
     astore
    -0.49
     ungef
    -0.48
    Зноскі
    -0.48
    jme
    -0.46
     kysy
    -0.45
     richied
    -0.44
     isInitialized
    -0.44
    ρχ
    -0.44
     Perlu
    -0.43
    POSITIVE LOGITS
     sad
    2.23
     sadness
    1.99
    Sad
    1.98
    sad
    1.91
     disappointed
    1.86
     Sad
    1.85
     saddest
    1.84
     disappointment
    1.84
     regret
    1.82
     saddened
    1.81
    Activations Density 0.402%

    No Known Activations