© 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. 3021
    Prev
    Next
    INDEX
    Explanations

    references to emotions and their impact on experiences and cognition

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

    emotions and feelings

    np_acts-logits-general · gemini-2.0-flash

    emotions and feelings

    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
    culata
    -0.45
    oredCriteria
    -0.45
    WaitGroup
    -0.44
    DataSnapshot
    -0.43
    zil
    -0.42
     économiques
    -0.42
    endió
    -0.42
     /*#__
    -0.42
    AutoSize
    -0.42
    کل
    -0.41
    POSITIVE LOGITS
     emotions
    2.43
     emotion
    2.32
     Emotions
    2.17
    Emotions
    1.98
     Emotion
    1.98
     emotional
    1.94
    emotions
    1.93
     feelings
    1.86
    emotion
    1.82
    Emotion
    1.76
    Activations Density 0.249%

    No Known Activations