© 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. 6-GEMMASCOPE-RES-16K
    11. 124
    Prev
    Next
    INDEX
    Explanations

    emotional states and reactions in people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.62
    PathVariable
    -0.50
    الحياه
    -0.50
     lent
    -0.48
    jarah
    -0.47
     &___
    -0.46
     թվական
    -0.46
    plash
    -0.45
    OMETRY
    -0.45
    cerol
    -0.44
    POSITIVE LOGITS
    ReusableCell
    0.62
     clearly
    0.61
    clearly
    0.61
     ciddi
    0.58
     comuniques
    0.58
     chiaramente
    0.57
    исленность
    0.57
    GeneratedValue
    0.56
    Clearly
    0.54
    skid
    0.54
    Activations Density 0.300%

    No Known Activations