© 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. 7-GEMMASCOPE-RES-16K
    11. 3184
    Prev
    Next
    INDEX
    Explanations

    phrases related to movie production and cast details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -0.64
     vägen
    -0.63
    CloseOperation
    -0.62
     svårt
    -0.59
     nationaux
    -0.58
     kvä
    -0.58
     skydd
    -0.56
     samfun
    -0.56
     tendances
    -0.54
     utveckling
    -0.52
    POSITIVE LOGITS
     INVOL
    1.04
     involving
    1.03
     involves
    0.96
     involve
    0.95
    volving
    0.88
    volves
    0.87
     invol
    0.86
    wherein
    0.83
     wherein
    0.82
     للاسماء
    0.81
    Activations Density 0.389%

    No Known Activations