© 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. 15-GEMMASCOPE-RES-16K
    11. 7893
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional responses and realizations related to interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.73
     themſelves
    -0.72
     defaultstate
    -0.63
     himſelf
    -0.61
     Jefus
    -0.61
    ?!”
    -0.60
     myſelf
    -0.60
    ſelf
    -0.59
     vocale
    -0.57
     Mourning
    -0.57
    POSITIVE LOGITS
    SharedCtor
    0.66
    脚注の使い方
    0.56
    Obrázky
    0.53
    tagHelperRunner
    0.52
    msgTypes
    0.51
    Autoritní
    0.51
     Pristupljeno
    0.51
     onCancelled
    0.50
    存于互联网档案馆
    0.50
    TemporalType
    0.49
    Activations Density 0.126%

    No Known Activations