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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4034
    Prev
    Next
    INDEX
    Explanations

    words related to connectivity and establishing connections

    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
    gdx
    -0.98
    Smarty
    -0.90
     UnityEditor
    -0.88
    ValueStyle
    -0.87
     vaut
    -0.87
    paravant
    -0.86
     présidenti
    -0.84
    adecimal
    -0.83
     GoogleFonts
    -0.83
    GraphicsUnit
    -0.82
    POSITIVE LOGITS
     connection
    1.41
     connections
    1.36
     CONNECT
    1.31
     Connection
    1.22
     conne
    1.22
     connectivity
    1.18
     Connections
    1.17
    connection
    1.16
     Conne
    1.16
     connects
    1.16
    Activations Density 0.049%

    No Known Activations